Search

The traditional method for transformer moisture diagnosis is to establish empirical equations between feature parameters extracted from frequency domain spectroscopy (FDS) and the transformer’s moisture content. However, the established empirical equation may not be applicable to a novel testing environment, resulting in an unreliable evaluation result. In this regard, it is acknowledged that FDS combined with machine learning is more suitable for estimating moisture content in a variety of test environments. Nonetheless, the accuracy of the estimation results obtained using the existing method is limited by the algorithm’s inability to generalize. To address this issue, we propose an AdaBoost algorithm-enhanced back-propagation neural network (BP_AdaBoost). This study creates a database by extracting feature parameters from the FDS that characterize the insulation states of the prepared samples. Then, using the BP_AdaBoost algorithm and the newly constructed database, the moisture estimation models are trained. Finally, the results of the estimation are discussed in terms of laboratory and field transformers. By comparing the proposed BP_AdaBoost algorithm to other intelligence algorithms, it is demonstrated that it not only performs better in generalization, but also maintains a high level of accuracy. [ABSTRACT FROM AUTHOR]

The Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. The vast majority of existing AUC-optimization-based machine learning methods only focus on binary-class cases, while leaving the multiclass cases unconsidered. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics. Our foundation is based on the M metric, which is a well-known multiclass extension of AUC. We first pay a revisit to this metric, showing that it could eliminate the imbalance issue from the minority class pairs. Motivated by this, we propose an empirical surrogate risk minimization framework to approximately optimize the M metric. Theoretically, we show that: (i) optimizing most of the popular differentiable surrogate losses suffices to reach the Bayes optimal scoring function asymptotically; (ii) the training framework enjoys an imbalance-aware generalization error bound, which pays more attention to the bottleneck samples of minority classes compared with the traditional $O(\sqrt{1/N})$ O (1 / N) result. Practically, to deal with the low scalability of the computational operations, we propose acceleration methods for three popular surrogate loss functions, including the exponential loss, squared loss, and hinge loss, to speed up loss and gradient evaluations. Finally, experimental results on 11 real-world datasets demonstrate the effectiveness of our proposed framework. The code is now available at https://github.com/joshuaas/Learning-with-Multiclass-AUC-Theory-and-Algorithms. [ABSTRACT FROM AUTHOR]

This paper studies an unmanned aerial vehicle (UAV)-assisted wireless powered IoT network, where a rotary-wing UAV adopts fly-hover-communicate protocol to successively visit IoT devices in demand. During the hovering periods, the UAV works on full-duplex mode to simultaneously collect data from the target device and charge other devices within its coverage. Practical propulsion power consumption model and non-linear energy harvesting model are taken into account. We formulate a multi-objective optimization problem to jointly optimize three objectives: maximization of sum data rate, maximization of total harvested energy and minimization of UAV’s energy consumption over a particular mission period. These three objectives are in conflict with each other partly and weight parameters are given to describe associated importance. Since IoT devices keep gathering information from the physical surrounding environment and their requirements to upload data change dynamically, online path planning of the UAV is required. In this paper, we apply deep reinforcement learning algorithm to achieve online decision. An extended deep deterministic policy gradient (DDPG) algorithm is proposed to learn control policies of UAV over multiple objectives. While training, the agent learns to produce optimal policies under given weights conditions on the basis of achieving timely data collection according to the requirement priority and avoiding devices’ data overflow. The verification results show that the proposed MODDPG (multi-objective DDPG) algorithm achieves joint optimization of three objectives and optimal policies can be adjusted according to weight parameters among optimization objectives. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of instrument current transformers technical state assessment based on machine learning methods. The introductory parts of the paper provide a detailed analysis of modern methods and approaches for technical state assessment of high-voltage power equipment of power plants and substations as well as a review of modern software tools and the latest trends in the given field of study. Justification of the relevance of the presented research aimed at instrument current transformers technical state assessment is provided along with the motivation for machine learning methods application for improvement of the accuracy and quality of high-voltage equipment state classification. Within the framework of the study, a comparative analysis of gradient boosting on decision trees and random forest algorithms was carried out for a given mathematical problem formulation. The main stages of processing the initial dataset are proposed as a step-by-step procedure, including feature extraction, feature transformation, feature interactions, etc. The outperforming efficiency of gradient boosting on decision trees algorithm was validated for real power equipment fleet. The resulting classification quality metrics of current transformers technical state assessment, Precision and Recall, are estimated to be 87.1% and 83.7%, correspondingly. [ABSTRACT FROM AUTHOR]

In real-world applications, it is important for machine learning algorithms to be robust against data outliers or corruptions. In this paper, we focus on improving the robustness of a large class of learning algorithms that are formulated as low-rank semi-definite programming (SDP) problems. Traditional formulations use the square loss, which is notorious for being sensitive to outliers. We propose to replace this with more robust noise models, including the $\ell _1$ ℓ 1 -loss and other nonconvex losses. However, the resultant optimization problem becomes difficult as the objective is no longer convex or smooth. To alleviate this problem, we design an efficient algorithm based on majorization-minimization. The crux is on constructing a good optimization surrogate, and we show that this surrogate can be efficiently obtained by the alternating direction method of multipliers (ADMM). By properly monitoring ADMM's convergence, the proposed algorithm is empirically efficient and also theoretically guaranteed to converge to a critical point. Extensive experiments are performed on four machine learning applications using both synthetic and real-world data sets. Results show that the proposed algorithm is not only fast but also has better performance than the state-of-the-arts. [ABSTRACT FROM AUTHOR]

This paper investigates the stochastic optimization problem focusing on developing scalable parallel algorithms for deep learning tasks. Our solution involves a reformation of the objective function for stochastic optimization in neural network models, along with a novel parallel computing strategy, coined the weighted aggregating stochastic gradient descent (WASGD). Following a theoretical analysis on the characteristics of the new objective function, WASGD introduces a decentralized weighted aggregating scheme based on the performance of local workers. Without any center variable, the new method automatically gauges the importance of local workers and accepts them by their contributions. Furthermore, we have developed an enhanced version of the method, WASGD+, by (1) implementing a designed sample order and (2) upgrading the weight evaluation function. To validate the new method, we benchmark our pipeline against several popular algorithms including the state-of-the-art deep neural network classifier training techniques (e.g., elastic averaging SGD). Comprehensive validation studies have been conducted on four classic datasets: CIFAR-100, CIFAR-10, Fashion-MNIST, and MNIST. Subsequent results have firmly validated the superiority of the WASGD scheme in accelerating the training of deep architecture. Better still, the enhanced version, WASGD+, is shown to be a significant improvement over its prototype. [ABSTRACT FROM AUTHOR]

For vehicle-to-network communications, handover (HO) management enables vehicles to maintain the connection with the network while transiting through coverage areas of different base stations (BSs). However, the high mobility of vehicles means shorter connection periods with each BS that leads to frequent HOs, hence raises the necessity for optimal HO decision making for high quality infotainment services. Machine learning is capable of capturing underlying pattern via data driven methods to find optimal solutions to complex problems, and much learning-based HO optimization research has been conducted focusing on specific network setups. However, attention still needs to be paid to the actual deployment aspect and standardized datasets or simulation environments for evaluation. This paper proposes a deep reinforcement learning-based HO algorithm using the input parameters that are configurable in the existing measurement report of cellular networks. The performance of the proposed algorithm is evaluated using the well-known network simulator ns-3 with its official LTE module. A realistic network setup in the city center of Glasgow (U.K.) is configured with vehicle trajectories generated by the routes mobility model using Google Maps Directions API. Evaluation results reveal that the proposed algorithm significantly outperforms the A3 RSRP baseline with an average of 25.72% packet loss reduction per HO, suggesting significant improvement in quality of service of phone call and video streaming, etc. The proposed algorithm also has a small implementation cost compared to some state-of-the-art and should be deployed by a software update to a local BS controller. [ABSTRACT FROM AUTHOR]

This paper considers stochastic convex optimization problems with two sets of constraints: (a) deterministic constraints on the domain of the optimization variable, which are difficult to project onto; and (b) deterministic or stochastic constraints that admit efficient projection. Problems of this form arise frequently in the context of semidefinite programming as well as when various NP-hard problems are solved approximately via semidefinite relaxation. Since projection onto the first set of constraints is difficult, it becomes necessary to explore projection-free algorithms, such as the stochastic Frank-Wolfe (FW) algorithm. On the other hand, the second set of constraints cannot be handled in the same way, and must be incorporated as an indicator function within the objective function, thereby complicating the application of FW methods. Similar problems have been studied before; however, they suffer from slow convergence rates. This work, equipped with momentum based gradient tracking technique, guarantees fast convergence rates on par with the best-known rates for problems without the second set of constraints. Zeroth-order variants of the proposed algorithms are also developed and again improve upon the state-of-the-art rate results. We further propose the novel trimmed FW variants that enjoy the same convergence rates as their classical counterparts, but are empirically shown to require significantly fewer calls to the linear minimization oracle speeding up the overall algorithm. The efficacy of the proposed algorithms is tested on relevant applications of sparse matrix estimation, clustering via semidefinite relaxation, and uniform sparsest cut problem. [ABSTRACT FROM AUTHOR]

In this paper, we study the formalism of unsupervised multi-class domain adaptation (multi-class UDA), which underlies a few recent algorithms whose learning objectives are only motivated empirically. Multi-Class Scoring Disagreement (MCSD) divergence is presented by aggregating the absolute margin violations in multi-class classification, and this proposed MCSD is able to fully characterize the relations between any pair of multi-class scoring hypotheses. By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains. Consequently, an algorithmic framework of Multi-class Domain-adversarial learning Networks (McDalNets) is developed, and its different instantiations via surrogate learning objectives either coincide with or resemble a few recently popular methods, thus (partially) underscoring their practical effectiveness. Based on our identical theory for multi-class UDA, we also introduce a new algorithm of Domain-Symmetric Networks (SymmNets), which is featured by a novel adversarial strategy of domain confusion and discrimination. SymmNets affords simple extensions that work equally well under the problem settings of either closed set, partial, or open set UDA. We conduct careful empirical studies to compare different algorithms of McDalNets and our newly introduced SymmNets. Experiments verify our theoretical analysis and show the efficacy of our proposed SymmNets. In addition, we have made our implementation code publicly available. [ABSTRACT FROM AUTHOR]

Dual Coordinate Descent (DCD) is one of the most popular optimization methods. The parallelization of DCD is difficult, as DCD is sequential in nature. As such, simultaneously running multiple DCD threads on batches of data elements causes result inaccuracy and slow convergence, due to the concurrent updates of multiple coordinates. Some parallelization methods adopt separable approximate functions that depend on the degree of parallelism. Such dependencies result in both poor scalability and slow-convergence. To address these challenges, in this paper we present a new parallel primal-dual algorithm for DCD, called PPD. In PPD, the block data distribution is utilized to obtain a new approximate function that is independent from the parallelism. Moreover, PPD is designed with a novel primal-dual acceleration scheme to approach the optimal solution closely and quickly. We demonstrate the advantages of PPD in terms of scalability and efficiency through experiments. [ABSTRACT FROM AUTHOR]

Dictionary learning has achieved remarkable success on a wide range of machine learning-based applications. In this paper, a locality-adaptive structured dictionary learning (LASDL) algorithm for cross-domain recognition is proposed. In the LASDL, a projective structured double reconstruction strategy is developed to train class-oriented sub-dictionaries from the specific classes of cross-domain samples. The strategy benefits to make full advantage of the discriminative information of cross-domain data and bridge the distribution divergence between two different domains. Meanwhile, an adaptive geometrical structure preserving function is designed to not only preserve the local manifold structures spanned by the representation coefficient spaces of the source and target domains, but also impose a constraint that the coefficients should keep closer to their class centers, which is propitious to reduce the distribution divergence and make the representation more accurate. With the structured linear coding technique, the final cross-domain recognition can be efficiently performed by determining class-specific reconstruction error. The optimization of the proposed LASDL model can be efficiently solved by simple least square method and alternating direction method of multipliers (ADMM) algorithm. Extensive experimental results validate the superiority of the proposed algorithm in contrast to other state-of-the-art predecessors. [ABSTRACT FROM AUTHOR]

We consider a class of nonconvex regularized optimization problems, which appear frequently in machine learning and data processing. Due to the structure of the problems, the iteratively reweighted algorithm was developed and applied to the consensus optimization. In this paper, we propose the acceleration of this scheme by adding an inertial term in each iteration. The proposed algorithms inherit the advantages of classical decentralized algorithms: they can be implemented over a connected network, in which the agents communicate with their neighbors and perform local computations. We also employ the diminishing stepsizes technique for the iteratively reweighted algorithm and consider its acceleration. In specific cases, our algorithms reduce to existing decentralized schemes and also indicate novel ones. Mathematically, we prove the convergence for both algorithms with several assumptions on the objective functions. With Kurdyka-Łojasiewicz property, convergence rates can be derived for constant stepsize case. Numerical results demonstrate the efficiency of the algorithms. [ABSTRACT FROM AUTHOR]

Temperature rising is an unavoidable effect on VLSI and has always been a critical issue in any system-on-chip – especially when targeting compute-intensive applications. This effect increases the delay in hardware accelerators, resulting in timing errors due to unsustainable clock frequency, whose impact must be carefully evaluated on design time to measure the performance degradation of the hardware accelerator. Further, a hardware operating at a higher temperature accelerates device aging, which incurs in more timing errors. This issue is usually addressed with the inclusion of timing guardbands that compensate for the deleterious effects of temperature, ensuring the hardware accelerator works within a reliable zone, i.e., without any timing errors caused by temperature effects at runtime. However, guardbands directly result in considerable performance and efficiency losses because the circuit will be clocked at a frequency lower than its full potential. Accelerators on edge devices often dismiss such guardbands to explore the full potential of the designed circuits, posing an enormous design challenge as this approach requires a careful evaluation of the impact of timing errors on the quality of the target applications. Many algorithms, such as in multimedia and machine learning applications, are capable of tolerating hardware errors. Yet, these algorithms have a dynamic behavior (i.e., closed-loop) where a timing error can be propagated, affecting subsequent steps. Measuring the degradation-induced errors in these applications is very challenging given that an accurate gate-level simulation to investigate degradation-induced timing errors needs to be coupled dynamically with a system-level simulator to unveil how induced errors in the underlying hardware ultimately impact the algorithm execution in the hardware accelerator. This is the first work to achieve this goal. State-of-the-art works have studied accelerators under timing-errors when removing (or narrowing) guardbands. However, their approach was suitable only for open-loop hardware accelerators which are entirely agnostic of complex interactions of the algorithms. Unlike prior work, this paper investigates temperature- and aging-induced timing-errors in the joint accelerator-algorithm interactions and their runtime impacts. Our framework investigates aging effects across the different layers starting from transistor physics all the way up to the algorithm layer. The hardware accelerator employed as a case study in this work is the sum of absolute differences (SAD), which is the most compute-intensive accelerator on commercial video encoder for mobile applications. Our results demonstrate the runtime behavior impacts of three advanced block-matching algorithms of the video encoder in a joint operation by a SAD accelerator under timing-errors induced by temperature and aging effects considering a 14nm FinFET technology. [ABSTRACT FROM AUTHOR]

This paper presents data-driven approaches to improve the active power output of wind turbines based on estimating their health condition. The main procedure includes estimations of fault degree and health condition level, and optimal power dispatch control. The proposed method can adjust the active power output of individual turbines according to their health condition and can thus optimize the total energy output of a wind farm. In the paper, extreme learning machine algorithm and Bonferroni interval are applied to estimate fault degree, while an analytic hierarchy process is used to estimate the health condition level. A scheme for power dispatch control is formulated based on the estimated health condition. Models have been identified from supervisory control and data acquisition data acquired from an operational wind farm, which contains temperature data of gearbox bearing and generator winding. The results show that the proposed method can maximize the operation efficiency of the wind farm while significantly reducing the fatigue loading on the faulty wind turbines. [ABSTRACT FROM AUTHOR]

In this paper, we propose to extend the standard Convolutional Dictionary Learning problem to a tensor representation where the activations are constrained to be “low-rank” through a Canonical Polyadic decomposition. We show that this additional constraint increases the robustness of the CDL with respect to noise and improve the interpretability of the final results. In addition, we discuss in detail the advantages of this representation and introduce two algorithms, based on ADMM or FISTA, that efficiently solve this problem. We show that by exploiting the low rank property of activations, they achieve lower complexity than the main CDL algorithms. Finally, we evaluate our approach on a wide range of experiments, highlighting the modularity and the advantages of this tensorial low-rank formulation. [ABSTRACT FROM AUTHOR]

Stochastic unit commitment is an efficient method for grid operation in the presence of significant uncertainties. An example is an operation during a predicted hurricane with uncertain line out-ages. However, the solution quality comes at the cost of substantial computational burden, which makes its adoption challenging. This paper evaluates some possible ways that machine learning can be used to reduce this computational burden. First, a set of feasibility studies is conducted. Results suggest that using machine learning as an assistant to the stochastic unit commitment solver is more advantageous than using it as a standalone solver. In particular, the machine learning model is trained to facilitate solving the problem by determining the unnecessary constraints that can be removed from the original problem without affecting the final accuracy. The variables that can be used as input features/predictors or outputs for the machine learning model are determined through feasibility studies. Then, an algorithm to train and utilize a machine learning model is proposed. The method is tested on a 500-bus synthetic South Carolina system. Various test cases show an average reduction in solution time by more than 90% by using the trained machine learning model to assist the stochastic unit commitment solver. [ABSTRACT FROM AUTHOR]

We consider the problem of minimizing the $\ell _1$ norm of a linear map over the sphere, which arises in various machine learning applications such as orthogonal dictionary learning (ODL) and robust subspace recovery (RSR). The problem is numerically challenging due to its nonsmooth objective and nonconvex constraint, and its algorithmic aspects have not been well explored. In this paper, we show how the manifold structure of the sphere can be exploited to design fast algorithms with provable guarantees for tackling this problem. Specifically, our contribution is fourfold. First, we present a manifold proximal point algorithm (ManPPA) for the problem and show that it converges at a global sublinear rate. Furthermore, we show that ManPPA can achieve a local quadratic convergence rate when applied to sharp instances of the problem. Second, we develop a semismooth Newton-based inexact augmented Lagrangian method for computing the search direction in each iteration of ManPPA and show that it has an asymptotic superlinear convergence rate. Third, we propose a stochastic variant of ManPPA called StManPPA, which is well suited for large-scale computation, and establish its sublinear convergence rate. Both ManPPA and StManPPA have provably faster convergence rates than existing subgradient-type methods. Fourth, using ManPPA as a building block, we propose a new heuristic method for solving a matrix analog of the problem, in which the sphere is replaced by the Stiefel manifold. The results from our extensive numerical experiments on the ODL and RSR problems demonstrate the efficiency and efficacy of our proposed methods. [ABSTRACT FROM AUTHOR]

Recent workat the U.S. Army CCDC Ground Vehicle Systems Center has shown that machine learning classifiers can quickly construct high-fidelity mobility maps. Training these classifiers, on the other hand, is still a challenge, since each data instance is labeled by performing a computationally intensive, physics-based simulation. In this paper we introduce an active learning framework, based on the query-by-bagging algorithm, that substantially reduces the number of simulations needed to train a classifier. Experimental results suggest that our sampling algorithm can train a neural network, with higher accuracy, using less than half the number of simulations when compared to random sampling. [ABSTRACT FROM AUTHOR]

Estimating set similarity and detecting highly similar sets are fundamental problems in areas such as databases and machine learning. MinHash is a well-known technique for approximating Jaccard similarity of sets and has been successfully used for many applications. Its two compressed versions, $b$ b -bit MinHash and Odd Sketch, can significantly reduce the memory usage of the MinHash, especially for estimating high similarities (i.e., similarities around 1). Although MinHash can be applied to static sets as well as streaming sets, of which elements are given in a streaming fashion, unfortunately, $b$ b -bit MinHash and Odd Sketch fail to deal with streaming data. To solve this problem, we previously designed a memory-efficient sketch method, MaxLogHash, to accurately estimate Jaccard similarities in streaming sets. Compared with MinHash, our method uses smaller sized registers (each register consists of less than 7 bits) to build a compact sketch for each set. In this paper, we further develop a faster method, MaxLogOPH++. Compared with MaxLogHash, MaxLogOPH++ reduces the time complexity for updating each coming element from $O(k)$ O (k) to $O(1)$ O (1) with a small additional memory. We conduct experiments on a variety of datasets, and experimental results demonstrate the efficiency and effectiveness of our methods. [ABSTRACT FROM AUTHOR]

Automated machine learning (AutoML) seeks to automatically find so-called machine learning pipelines that maximize the prediction performance when being used to train a model on a given dataset. One of the main and yet open challenges in AutoMLis an effective use of computational resources: An AutoML process involves the evaluation of many candidate pipelines, which are costly but often ineffective because they are canceled due to a timeout. In this paper, we present an approach to predict the runtime of two-step machine learning pipelines with up to one pre-processor, which can be used to anticipate whether or not a pipeline will time out. Separate runtime models are trained offline for each algorithm that may be used in a pipeline, and an overall prediction is derived from these models. We empirically show that the approach increases successful evaluations made by an AutoML tool while preserving or even improving on the previously best solutions. [ABSTRACT FROM AUTHOR]

In this paper, we present a framework for performing automatic analysis of Land Use Zones based on Location-Based Social Networks (LBSNs). We model city areas using a hierarchical structure of POIs extracted from foursquare. We encode such structures in kernel machines, e.g., Support Vector Machines, using a new Tree Kernel, i.e., the Hierarchical POI Kernel (HPK), which can take the importance of the individual POIs into account during the substructure matching. This way, HPK projects structures in the space of all their possible substructures such that each dimension corresponds to a semantic structural feature, weighted according to the discriminative power of POIs. We generated four different datasets for the following cities: Barcelona, Lisbon, Amsterdam and Milan, where we trained and tested our models. The results show that our approach largely outperforms previous work and standard baseline built on simple features, such as counts of different POIs. Finally, we apply a mining algorithm to extract the most relevant features (tree fragments) from the implicit TK space according to the weights the kernel machine assigned to them. Our approach can produce an explicit set of representative features that can be used to classify and characterize urban areas. [ABSTRACT FROM AUTHOR]

Publishing datasets plays an essential role in open data research and promoting transparency of government agencies. However, such data publication might reveal users’ private information. One of the most sensitive sources of data is spatiotemporal trajectory datasets. Unfortunately, merely removing unique identifiers cannot preserve the privacy of users. Adversaries may know parts of the trajectories or be able to link the published dataset to other sources for the purpose of user identification. Therefore, it is crucial to apply privacy preserving techniques before the publication of spatiotemporal trajectory datasets. In this paper, we propose a robust framework for the anonymization of spatiotemporal trajectory datasets termed as machine learning based anonymization (MLA). By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use k-means algorithm for this purpose. A variation of k-means algorithm is also proposed to preserve the privacy in overly sensitive datasets. Moreover, we improve the alignment process by considering multiple sequence alignment as part of the MLA. The framework and all the proposed algorithms are applied to T-Drive, Geolife, and Gowalla location datasets. The experimental results indicate a significantly higher utility of datasets by anonymization based on MLA framework. [ABSTRACT FROM AUTHOR]

Multi-label classification is an important research topic in machine learning, for which exploiting label dependencies is an effective modeling principle. Recently, probabilistic models have shown great potential in discovering dependencies among labels. In this paper, motivated by the recent success of multi-view learning to improve the generalization performance, we propose a novel multi-view probabilistic model named latent conditional Bernoulli mixture (LCBM) for multi-label classification. LCBM is a generative model taking features from different views as inputs, and conditional on the latent subspace shared by the views a Bernoulli mixture model is adopted to build label dependencies. Inside each component of the mixture, the labels have a weak correlation which facilitates computational convenience. The mean field variational inference framework is used to carry out approximate posterior inference in the probabilistic model, where we propose a Gaussian mixture variational autoencoder (GMVAE) for effective posterior approximation. We further develop a scalable stochastic training algorithm for efficiently optimizing the model parameters and variational parameters, and derive an efficient prediction procedure based on greedy search. Experimental results on multiple benchmark datasets show that our approach outperforms other state-of-the-art methods under various metrics. [ABSTRACT FROM AUTHOR]

With growth in the number of smart devices and advancements in their hardware, in recent years, data-driven machine learning techniques have drawn significant attention. However, due to privacy and communication issues, it is not possible to collect this data at a centralized location. Federated learning is a machine learning setting where the centralized location trains a learning model over remote devices. Federated learning algorithms cannot be employed in the real world scenarios unless they consider unreliable and resource-constrained nature of the wireless medium. In this paper, we propose a federated learning algorithm that is suitable for cellular wireless networks. We prove its convergence, and provide a sub-optimal scheduling policy that improves the convergence rate. We also study the effect of local computation steps and communication steps on the convergence of the proposed algorithm. We prove, in practice, federated learning algorithms may solve a different problem than the one that they have been employed for if the unreliability of wireless channels is neglected. Finally, through numerous experiments on real and synthetic datasets, we demonstrate the convergence of our proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper presents a novel methodology for the construction of a transient stability boundary (TSB) that overcomes the lack of TSB analytical description for multiple operating states and contingencies in power systems. The proposed approach models the TSB as a nonlinear mapping between the system parameters of interest and the corresponding critical clearing time (CCT). This compact mathematical expression is built based on an efficient discriminative network, broad learning system (BLS). While keeping a high accuracy and generalization ability, the newly introduced construction method provides an efficient update strategy that does not require an entire retraining cycle. These properties make this method suitable for online transient stability assessment (TSA). The prospects of the developed method are verified via case studies by employing the IEEE 9-bus, IEEE 39-bus (New England) test systems and a real system of China Southern Power Grid. In comparison with existing methods, the newly introduced algorithm has a higher prediction accuracy and improved robustness. The demonstrated characteristics indicate that the proposed method may serve as a valuable tool in the framework of online TSA. [ABSTRACT FROM AUTHOR]

As the training dataset size and the model size of machine learning increase rapidly, more computing resources are consumed to speedup the training process. However, the scalability and performance reproducibility of parallel machine learning training, which mainly uses stochastic optimization algorithms, are limited. In this paper, we demonstrate that the sample difference in the dataset plays a prominent role in the scalability of parallel machine learning algorithms. We propose to use statistical properties of dataset to measure sample differences. These properties include the variance of sample features, sample sparsity, sample diversity, and similarity in sampling sequences. We choose four types of parallel training algorithms as our research objects: (1) the asynchronous parallel SGD algorithm (Hogwild! algorithm), (2) the parallel model average SGD algorithm (minibatch SGD algorithm), (3) the decentralization optimization algorithm, and (4) the dual coordinate optimization (DADM algorithm). Our results show that the statistical properties of training datasets determine the scalability upper bound of these parallel training algorithms. [ABSTRACT FROM AUTHOR]

Underwater environments create a challenging channel for communications. In this paper, we design a novel receiver system by exploring the machine learning technique–Deep Belief Network (DBN) – to combat the signal distortion caused by the Doppler effect and multi-path propagation. We evaluate the performance of the proposed receiver system in both simulation experiments and sea trials. Our proposed receiver system comprises of DBN based de-noising and classification of the received signal. First, the received signal is segmented into frames before the each of these frames is individually pre-processed using a novel pixelization algorithm. Then, using the DBN based de-noising algorithm, features are extracted from these frames and used to reconstruct the received signal. Finally, DBN based classification of the reconstructed signal occurs. Our proposed DBN based receiver system does show better performance in channels influenced by the Doppler effect and multi-path propagation with a performance improvement of 13.2dB at 10−3 Bit Error Rate (BER). [ABSTRACT FROM AUTHOR]

Recently, maximum correntropy criterion (MCC) has been widely and successfully used in robust signal processing and machine learning, in which the correntropy is maximized instead of minimizing the popular mean square error (MSE) to improve the robustness with respect to outliers or impulsive noises. A lot of efforts have been devoted to derive different adaptive algorithms under MCC, but to date, little insight has been gained as to how the MCC solution will be influenced by outliers. In this paper, we investigate this problem and our focus is mainly on the parameter estimation of a simple linear errors-in-variables (EIVs) model with scalar variables. Under some conditions, we derive an upper bound on the absolute value of the estimation error and show that the MCC solution can get very close to the true value of the unknown parameter even with arbitrarily large outliers in both the input and output variables. Illustrative examples are provided to verify and clarify the theory. [ABSTRACT FROM AUTHOR]

Linear spectral unmixing is the practice of decomposing the mixed pixel into a linear combination of the constituent endmembers and the estimated abundances. This paper focuses on unsupervised spectral unmixing where the endmembers are unknown a priori. Conventional approaches use either geometrical- or statistical-based approaches. In this paper, we address the challenges of spectral unmixing with unsupervised deep learning models, in specific, the autoencoder models, where the decoder serves as the endmembers and the hidden layer output serves as the abundances. In several recent attempts, part-based autoencoders have been designed to solve the unsupervised spectral unmixing problem. However, the performance has not been satisfactory. In this paper, we first discuss some important findings we make on issues with part-based autoencoders. By proof of counterexample, we show that all existing part-based autoencoder networks with nonnegative and tied encoder and decoder are inherently defective by making these inappropriate assumptions on the network structure. As a result, they are not suitable for solving the spectral unmixing problem. We propose a so-called untied denoising autoencoder with sparsity, in which the encoder and decoder of the network are independent, and only the decoder of the network is enforced to be nonnegative. Furthermore, we make two critical additions to the network design. First, since denoising is an essential step for spectral unmixing, we propose to incorporate the denoising capacity into the network optimization in the format of a denoising constraint rather than cascading another denoising preprocessor in order to avoid the introduction of additional reconstruction error. Second, to be more robust to the inaccurate estimation of a number of endmembers, we adopt an $l_{21}$ -norm on the encoder of the network to reduce the redundant endmembers while decreasing the reconstruction error simultaneously. The experimental results demonstrate that the proposed approach outperforms several state-of-the-art methods, especially for highly noisy data. [ABSTRACT FROM AUTHOR]

Hyperspectral imagery (HSI) has shown promising results in real-world applications. However, the technological evolution of optical sensors poses two main challenges in HSI classification: 1) the spectral band is usually redundant and noisy and 2) HSI with millions of pixels has become increasingly common in real-world applications. Motivated by the recent success of hybrid huberized support vector machines (HHSVMs), which inherit the benefits of both lasso and ridge regression, this paper first investigates the advantages of HHSVM for HSI applications. Unfortunately, the existing HHSVM solvers suffer from prohibitive computational costs on large-scale data sets. To solve this problem, this paper proposes simple and effective stochastic HHSVM algorithms for HSI classification. In the stochastic settings, we show that with a probability of at least $1-\varrho $ , our algorithms find an $\epsilon $ -accurate solution using $\tilde {O}({1}/{\lambda _{2}\epsilon })$ iterations. Since the convergence rate of our algorithms does not depend on the size of the training set, our algorithms are suitable for handling large-scale problems. We demonstrate the superiority of our algorithms by conducting experiments on large-scale binary and multiclass classification problems, comparing to the state-of-the-art HHSVM solvers. Finally, we apply our algorithms to real HSI classification and achieve promising results. [ABSTRACT FROM AUTHOR]

Ridge regression (RR) is an important machine learning technique which introduces a regularization hyperparameter α to ordinary multiple linear regression for analyzing data suffering from multicollinearity. In this paper, we present a quantum algorithm for RR, where the technique of parallel Hamiltonian simulation to simulate a number of Hermitian matrices in parallel is proposed and used to develop a quantum version of K-fold cross-validation approach, which can efficiently estimate the predictive performance of RR. Our algorithm consists of two phases: (1) using quantum K-fold cross-validation to efficiently determine a good α with which RR can achieve good predictive performance, and then (2) generating a quantum state encoding the optimal fitting parameters of RR with such α , which can be further utilized to predict new data. Since indefinite dense Hamiltonian simulation has been adopted as a key subroutine, our algorithm can efficiently handle non-sparse data matrices. It is shown that our algorithm can achieve exponential speedup over the classical counterpart for (low-rank) data matrices with low condition numbers. But when the condition numbers of data matrices are large to be amenable to full or approximately full ranks of data matrices, only polynomial speedup can be achieved. [ABSTRACT FROM AUTHOR]

The emergence of big data has caused a dramatic shift in the operating regime for optimization algorithms. The performance bottleneck, which used to be computations, is now often communications. Several gradient compression techniques have been proposed to reduce the communication load at the price of a loss in solution accuracy. Recently, it has been shown how compression errors can be compensated for in the optimization algorithm to improve the solution accuracy. Even though convergence guarantees for error-compensated algorithms have been established, there is very limited theoretical support for quantifying the observed improvements in solution accuracy. In this paper, we show that Hessian-aided error compensation, unlike other existing schemes, avoids accumulation of compression errors on quadratic problems. We also present strong convergence guarantees of Hessian-based error compensation for stochastic gradient descent. Our numerical experiments highlight the benefits of Hessian-based error compensation, and demonstrate that similar convergence improvements are attained when only a diagonal Hessian approximation is used. [ABSTRACT FROM AUTHOR]

Multi-view learning (MVL) is an active direction in machine learning that aims at exploiting the consensus and complementarity information among multiple distinct feature sets to boost the generalization performance of the counterpart algorithm. So far, two classical SVM-based MVL methods are SVM-2K and multi-view twin support vector machine (MvTSVM). They are designed only for two-view classification and cannot tackle the general multi-view classification problem. They also cannot effectively leverage the complementarity information among different feature views. In this paper, we propose two novel multi-view support vector machines with the consensus and complementarity information for MVL that not only can deal with the two-view classification problem but also the general multi-view classification problem by jointly learning multiple different views in a non-pairwise way. The disagreement among different views is regarded as a constraint or a regularization term in the objective function which plays an important role in exploring the consensus information. Combination weights for the reconstruction of each view in regularization terms are learned to explore complementarity information among different views. Finally, an efficient iteration algorithm with the classical convex quadratic programming is developed for optimization. Experimental results validate the effectiveness of our proposed methods. [ABSTRACT FROM AUTHOR]

The problem of completing a large low rank matrix using a subset of revealed entries has received much attention in the last ten years. The main result of this paper gives a necessary and sufficient condition, stated in the language of graph limit theory, for a sequence of matrix completion problems with arbitrary missing patterns to be asymptotically solvable. It is then shown that a small modification of the Candès–Recht nuclear norm minimization algorithm provides the required asymptotic solution whenever the sequence of problems is asymptotically solvable. The theory is fully deterministic, with no assumption of randomness. A number of open questions are listed. [ABSTRACT FROM AUTHOR]

In this paper, a new metric learning algorithm is proposed to improve face verification and person re-identification in RGB images by learning from RGB and Depth (RGB-D) training images. We address this problem by formulating it as a Learning Using Privileged Information problem, in which the additional depth images associated with the RGB training images are not available for the testing process. Based on the large margin nearest neighbor (LMNN) classification framework, we propose an effective metric learning method called large margin nearest neighbor classification with privileged information (LMNN+) by incorporating depth information to improve decision function learning in the training process. Specifically, two distance metrics based on visual features as well as depth features are jointly learned by minimizing the triplet loss in which the within-class difference is minimized, while the between-class difference is maximized. The distances in the depth feature space can be utilized to guide the training process in the visual feature space. In addition, we propose an efficient optimization method which can handle billions of constraints in the optimization problem of LMNN+. The comprehensive experiments on the EUROCOM data set, the CurtinFaces data set as well as the BIWI RGBD-ID data set demonstrate the effectiveness of our algorithm for face verification and person re-identification by leveraging privileged information. [ABSTRACT FROM AUTHOR]

This paper proposes a methodology for predicting online rotor angle stability in power system operation under significant contribution from wind generation. First, a novel algorithm is developed to extract a stability index (SI) that quantifies the margin of rotor angle stability of power systems reflecting the dynamics of wind power. An approach is proposed that takes advantage of the machine learning technique and the newly defined SI. In case of a contingency, the developed algorithm is employed in parallel to find SIs for all possible instability modes. The SIs are formed as a vector and then applied to a classifier algorithm for rotor angle stability prediction. Compared to other features used in state-of-the-art methods, SI vectors are highly recognizable and thus can lead to a more accurate and reliable prediction. The proposed approach is validated on two IEEE test systems with various wind power penetration levels and compared to existing methods, followed by a discussion of results. [ABSTRACT FROM AUTHOR]

In order to improve the efficiency and comfort of autonomous vehicles while ensuring safety, the decision algorithm needs to interact with human drivers, infer the most probable behavior and then makes advantageous decision. This paper proposes a Nash-Q learning based motion decision algorithm to consider the interaction. First, the local trajectory of surrounding vehicle is predicted by kinematic constraints, which can reflect the short-term motion trend. Then, the future action space is built based the predicted local trajectory that consists of five basis actions. With that, the Nash-Q learning process can be implemented by the game between these basis actions. By elimination of strictly dominated actions and the Lemke-Howson method, the autonomous vehicle can decide the optimal action and infer the behavior of surrounding vehicle. Finally, the lane merging scenario is built to test the performance contrast to the existing methods. The driver in loop experiment is further designed to verify the interaction performance in multi-vehicle traffic. The results show that the Nash-Q learning based algorithm can improve the efficiency and comfort by 15.75% and 20.71% to the Stackelberg game and the no-interaction method respectively while the safety is ensured. It can also make real-time interaction with human drivers in multi-vehicle traffic. [ABSTRACT FROM AUTHOR]

In multi-user downlink small cell networks, cooperative resource allocation (RA) within a small cell cluster is a key technique to enhance network capacity. However, capacity-maximizing RA in frequency-selective fading channels requires global channel state information (CSI) of users within a small cell cluster, which makes it infeasible in practical networks with limited direct link capacity. To circumvent this global CSI assumption, most of the existing studies on RA have been based on several CSI assumptions such as local CSI and local CSI at the transmitters (CSIT). Nevertheless, cost functions with local CSI or local CSIT in the literature rely on heuristic formulations, because the sum-rate cannot be computed if without global CSI. In this paper, we propose a deep reinforcement learning-based RA algorithm to maximize the sum-rate for any given limited information on instantaneous CSI or sum-rate at the previous period. The proposed scheme is not restricted to certain CSI assumptions, but attempts to find the best RA for any given information such as quantized local CSI and quantized local CSIT; thus, it is applicable to any given direct link capacity. The proposed algorithm is self-adaptive in time-varying channels, since it is not divided into training and test phases. We modify the target neural network (TNN) scheme to enhance the sum-rate and the convergence speed. Numerical simulations confirm that: i) the proposed algorithm outperforms the conventional algorithms even under the same CSI assumption such as local CSI and local CSIT; ii) a flexible trade-off between the amount of CSI and the sum-rate is realizable in practical systems. [ABSTRACT FROM AUTHOR]

Trailer mass is one of the important trailer parameters that affects the stability of the tractor-trailer systems. In this paper, two different approaches are proposed to estimate trailer mass for arbitrary tractor-trailer configurations; dynamic system model-based and Machine Learning (ML) approaches. The stability of the dynamic system model-based estimation algorithm is analyzed, establishing the convergence of the estimation error to zero. In the proposed ML-based approach, a Deep Neural Network (DNN) is designed to estimate trailer mass. The inputs of the ML-based method have been selected based on the tractor-trailer dynamic model, and are considered to be normalized by the tractor mass, tire sizes, and geometry so that re-training of the network is not needed for different towing vehicles. The simulation and experimental results justify the accuracy of the trailer mass estimation in various cases and demonstrate that the trailer mass can be estimated with less than 10% error. [ABSTRACT FROM AUTHOR]

Colonoscopy is tool of choice for preventing Colorectal Cancer, by detecting and removing polyps before they become cancerous. However, colonoscopy is hampered by the fact that endoscopists routinely miss 22-28% of polyps. While some of these missed polyps appear in the endoscopist’s field of view, others are missed simply because of substandard coverage of the procedure, i.e. not all of the colon is seen. This paper attempts to rectify the problem of substandard coverage in colonoscopy through the introduction of the C2D2 (Colonoscopy Coverage Deficiency via Depth) algorithm which detects deficient coverage, and can thereby alert the endoscopist to revisit a given area. More specifically, C2D2 consists of two separate algorithms: the first performs depth estimation of the colon given an ordinary RGB video stream; while the second computes coverage given these depth estimates. Rather than compute coverage for the entire colon, our algorithm computes coverage locally, on a segment-by-segment basis; C2D2 can then indicate in real-time whether a particular area of the colon has suffered from deficient coverage, and if so the endoscopist can return to that area. Our coverage algorithm is the first such algorithm to be evaluated in a large-scale way; while our depth estimation technique is the first calibration-free unsupervised method applied to colonoscopies. The C2D2 algorithm achieves state of the art results in the detection of deficient coverage. On synthetic sequences with ground truth, it is 2.4 times more accurate than human experts; while on real sequences, C2D2 achieves a 93.0% agreement with experts. [ABSTRACT FROM AUTHOR]

The automatic detection of buried threats in ground penetrating radar (GPR) data is an active area of research due to GPR's ability to detect both metal and nonmetal subsurface objects. Recent work on algorithms designed to distinguish between threats and nonthreats in GPR data has utilized computer vision methods to advance the state-of-the-art detection and discrimination performance. Feature extractors, or descriptors, from the computer vision literature have exhibited excellent performance in representing 2-D GPR image patches and allow for robust classification of threats from nonthreats. This paper aims to perform a broad study of feature extraction methods in order to identify characteristics that lead to improved classification performance under controlled conditions. The results presented in this paper show that gradient-based features, such as the edge histogram descriptor and the scale invariant feature transform, provide the most robust performance across a large and varied data set. These results indicate that various techniques from the computer vision literature can be successfully applied to target detection in GPR data and that more advanced techniques from the computer vision literature may provide further performance improvements. [ABSTRACT FROM PUBLISHER]

This paper presents a method to improve the traditional mixture of deformable part models (MDPM) method from the learning perspective. First, an object part configuration learning algorithm based on group sparsity constraint is introduced to automatically discover the object part number, size, and location. The algorithm imposes two additional regularization terms in addition to the standard hinge loss function. The first term focuses on automatic part selection and the second term focuses on automatic part placement. Second, this paper introduces an improved MDPM training framework. The framework applies a learned transformation to normalize the prediction score from each individual deformable part model (DPM) into a pseudo probability such that the partition of the entire object appearance feature space becomes less sensitive to the prior distributions of different DPMs. Finally, the two proposed improvements are combined and formulated under the expectation-maximization framework. We evaluate our method mainly using the PASCAL VOC2007 and VOC2010 detection benchmarks and show that the proposed learning algorithms could increase the detection mean AP score by 2.4% and 0.9%, respectively, on these two data sets when using the proposed part selection method and the training algorithm. We also present further in-depth analysis of the proposed algorithm in the experiments. [ABSTRACT FROM PUBLISHER]

In this paper, a deep reinforcement learning-based robust control strategy for quadrotor helicopters is proposed. The quadrotor is controlled by a learned neural network which directly maps the system states to control commands in an end-to-end style. The learning algorithm is developed based on the deterministic policy gradient algorithm. By introducing an integral compensator to the actor-critic structure, the tracking accuracy and robustness have been greatly enhanced. Moreover, a two-phase learning protocol which includes both offline and online learning phase is proposed for practical implementation. An offline policy is first learned based on a simplified quadrotor model. Then, the policy is online optimized in actual flight. The proposed approach is evaluated in the flight simulator. The results demonstrate that the offline learned policy is highly robust to model errors and external disturbances. It also shows that the online learning could significantly improve the control performance. [ABSTRACT FROM AUTHOR]

Graph based classification methods have been widely applied in the fields of computer vision and machine learning. The quality of the graph highly affects the performance of these methods. The same object is commonly represented by different features, i.e., multi-view features, which leads to multiple graphs corresponding to different features in multi-view learning. However, what kind of graph is important for the task is unknown in advance. Moreover, existing multi-view learning methods become weak in dealing with noisy graphs when the data is corrupted by the noise. In this paper, we address this problem by observing that the noise of each graph has specific structure. Then, based on this observation we propose a robust multi-view graph recovery (RMGR) method in which the specific structure is used to clean the multiple input noisy graphs and these cleaned graphs are simultaneously aggregated into a consensus graph by adaptively assigning great weighted coefficients for important graphs. To make the consensus graph suit classification, the clustering structure is introduced to restrain the rank of Laplacian matrix of the consensus graph such that the number of its connected components is equal to that of clustering. In doing so, the graph is adaptively adjusted during optimization to more accurately partition data. The optimization problem is solved by proposed the iterative update algorithm. Extensive experiments on synthetic and several benchmark data sets show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Confronted with considerable intermittence and variability of wind power, prediction intervals (PIs) serve as a crucial tool to assist power system decision-making under uncertainties. Conventional PIs rely on predetermining the lower and upper quantile proportions and therefore suffer from conservative interval width. This paper innovatively develops a chance constrained extreme learning machine (CCELM) model to generate quality nonparametric proportion-free PIs of wind power generation, which minimizes the expected interval width subject to the PI coverage probability constraint. Due to the independency on the preset PI bounds proportions, the proposed CCELM model merits high adaptivity and taps the latent potentialities for PI shortening. The convexity of extreme learning machine renders the sample average approximation counterpart of stochastic CCELM model equivalent to a parameter searching task in parametric optimization problem with polyhedral feasible region. A novel difference of convex functions optimization based bisection search (DCBS) algorithm is proposed to efficiently construct the CCELM model, which successfully realizes machine learning by means of solving linear programming problems sequentially. Comprehensive numerical experiments based on actual wind farm data demonstrate the significant effectiveness and efficiency of the developed CCELM model and DCBS algorithm. [ABSTRACT FROM AUTHOR]

Human mobility prediction techniques are instrumental for many important applications including service management and city planning. Previous work looks at the inherent patterns of a user's historical trajectories to predict his/her future location. Such method suffers when only a small number of historical locations are available, which is a main challenge for mobility prediction on sparse trajectory datasets. In this paper, we propose a multi-task learning based algorithm to predict users’ mobility by learning the mobility behaviors of different users at the same time and exploiting the similarities among them to overcome the sparse issue and improve the prediction performance. Specifically, we use a Bayesian mixture model to describe users’ spatio-temporal mobility patterns, where we introduce a novel von Mises distribution to model the temporal distribution of users’ mobility to better preserve its continuity across time. Then, we use the hierarchical Dirichlet process to perform joint prediction of all users’ mobility. This model allows us to leverage similar mobility patterns among users to improve the prediction performance for users with sparse trajectory data. We conduct extensive evaluations using data collected by a cellular network operator and mobile applications. Our evaluations show that our algorithms achieve prediction accuracy of 53.9% on average and 73.2% for users with high-quality mobility data, with the performance gap over 8.7% on average compared with the state-of-the-art algorithms, demonstrating the effectiveness of our proposed algorithm. [ABSTRACT FROM AUTHOR]

Dynamic functional connectivity (dFC) analysis using resting-state functional Magnetic Resonance Imaging (rs-fMRI) is currently an advanced technique for capturing the dynamic changes of neural activities in brain disease identification. Most existing dFC modeling methods extract dynamic interaction information by using the sliding window-based correlation, whose performance is very sensitive to window parameters. Because few studies can convincingly identify the optimal combination of window parameters, sliding window-based correlation may not be the optimal way to capture the temporal variability of brain activity. In this paper, we propose a novel adaptive dFC model, aided by a deep spatial-temporal feature fusion method, for mild cognitive impairment (MCI) identification. Specifically, we adopt an adaptive Ultra-weighted-lasso recursive least squares algorithm to estimate the adaptive dFC, which effectively alleviates the problem of parameter optimization. Then, we extract temporal and spatial features from the adaptive dFC. In order to generate coarser multi-domain representations for subsequent classification, the temporal and spatial features are further mapped into comprehensive fused features with a deep feature fusion method. Experimental results show that the classification accuracy of our proposed method is reached to 87.7%, which is at least 5.5% improvement than the state-of-the-art methods. These results elucidate the superiority of the proposed method for MCI classification, indicating its effectiveness in the early identification of brain abnormalities. [ABSTRACT FROM AUTHOR]

In this paper, we study a real-time monitoring system in which multiple source nodes are responsible for sending update packets to a common destination node in order to maintain the freshness of information at the destination. Since it may not always be feasible to replace or recharge batteries in all source nodes, we consider that the nodes are powered through wireless energy transfer (WET) by the destination. For this system setup, we investigate the optimal online sampling policy (referred to as the age-optimal policy) that jointly optimizes WET and scheduling of update packet transmissions with the objective of minimizing the long-term average weighted sum of Age of Information (AoI) values for different physical processes (observed by the source nodes) at the destination node, referred to as the sum-AoI. To solve this optimization problem, we first model this setup as an average cost Markov decision process (MDP) with finite state and action spaces. Due to the extreme curse of dimensionality in the state space of the formulated MDP, classical reinforcement learning algorithms are no longer applicable to our problem even for reasonable-scale settings. Motivated by this, we propose a deep reinforcement learning (DRL) algorithm that can learn the age-optimal policy in a computationally-efficient manner. We further characterize the structural properties of the age-optimal policy analytically, and demonstrate that it has a threshold-based structure with respect to the AoI values for different processes. We extend our analysis to characterize the structural properties of the policy that maximizes average throughput for our system setup, referred to as the throughput-optimal policy. Afterwards, we analytically demonstrate that the structures of the age-optimal and throughput-optimal policies are different. We also numerically demonstrate these structures as well as the impact of system design parameters on the optimal achievable average weighted sum-AoI. [ABSTRACT FROM AUTHOR]