Search

Generative models have gained significant attention in multivariate time series forecasting (MTS), particularly due to their ability to generate high-fidelity samples. Forecasting the probability distribution of multivariate time series is a challenging yet practical task. Although some recent attempts have been made to handle this task, two major challenges persist: 1) some existing generative methods underperform in high-dimensional multivariate time series forecasting, which is hard to scale to higher dimensions; 2) the inherent high-dimensional multivariate attributes constrain the forecasting lengths of existing generative models. In this paper, we point out that discrete token representations can model high-dimensional MTS with faster inference time, and forecasting the target with long-term trends of itself can extend the forecasting length with high accuracy. Motivated by this, we propose a vector quantized framework called Hierarchical Discrete Transformer (HDT) that models time series into discrete token representations with l2 normalization enhanced vector quantized strategy, in which we transform the MTS forecasting into discrete tokens generation. To address the limitations of generative models in long-term forecasting, we propose a hierarchical discrete Transformer. This model captures the discrete long-term trend of the target at the low level and leverages this trend as a condition to generate the discrete representation of the target at the high level that introduces the features of the target itself to extend the forecasting length in high-dimensional MTS. Extensive experiments on five popular MTS datasets verify the effectiveness of our proposed method.

In this paper we obtain a verifiable sufficient condition for a polyhedral multifunction to be Lipschitz continuous on its domain. We apply this sufficient condition to establish the Lipschitz continuity of the solution multifunction for an extended $\ell_1$ regularization problem with respect to the regularization parameter and the observation parameter under the assumption that the data matrix is of full row rank. In doing so, we show that the solution multifunction is a polyhedral one by expressing its graph as the union of the polyhedral cones constructed by the index sets defined by nonempty faces of the feasible set of an extended dual $\ell_1$ regularization problem. We demonstrate that the domain of the solution multifunction is partitioned as the union of the projections of the above polyhedral cones onto the parameters space and that the graph of the restriction of the multifunction on each of these projections is convex. In comparing with the existing result of the local Lipschitz continuity of the Lasso problem in the literature where certain linear independence condition was assumed, our condition (i.e., full row rank of data matrix) is very weak and our result (i.e., Lipschitz continuity on the domain) is much more stronger. As corollaries of the Lipschitz continuity of the solution multifunction, we show that the single-valuedness and linearity (or piecewise linearity) of the solution multifunction on a particular polyhedral set of the domain are equivalent to certain linear independence conditions of the corresponding columns of the data matrix proposed in the literature., Comment: 25 pages, 1 figure

Test-time adaptation has proven effective in adapting a given trained model to unseen test samples with potential distribution shifts. However, in real-world scenarios, models are usually deployed on resource-limited devices, e.g., FPGAs, and are often quantized and hard-coded with non-modifiable parameters for acceleration. In light of this, existing methods are often infeasible since they heavily depend on computation-intensive backpropagation for model updating that may be not supported. To address this, we propose a test-time Forward-Optimization Adaptation (FOA) method. In FOA, we seek to solely learn a newly added prompt (as model's input) via a derivative-free covariance matrix adaptation evolution strategy. To make this strategy work stably under our online unsupervised setting, we devise a novel fitness function by measuring test-training statistic discrepancy and model prediction entropy. Moreover, we design an activation shifting scheme that directly tunes the model activations for shifted test samples, making them align with the source training domain, thereby further enhancing adaptation performance. Without using any backpropagation and altering model weights, FOA runs on quantized 8-bit ViT outperforms gradient-based TENT on full-precision 32-bit ViT, while achieving an up to 24-fold memory reduction on ImageNet-C., Comment: 18 pages, 4 figures, 17 tables, accepted by International Conference on Machine Learning

In response to the limitations of reinforcement learning and evolutionary algorithms (EAs) in complex problem-solving, Evolutionary Reinforcement Learning (EvoRL) has emerged as a synergistic solution. EvoRL integrates EAs and reinforcement learning, presenting a promising avenue for training intelligent agents. This systematic review firstly navigates through the technological background of EvoRL, examining the symbiotic relationship between EAs and reinforcement learning algorithms. We then delve into the challenges faced by both EAs and reinforcement learning, exploring their interplay and impact on the efficacy of EvoRL. Furthermore, the review underscores the need for addressing open issues related to scalability, adaptability, sample efficiency, adversarial robustness, ethic and fairness within the current landscape of EvoRL. Finally, we propose future directions for EvoRL, emphasizing research avenues that strive to enhance self-adaptation and self-improvement, generalization, interpretability, explainability, and so on. Serving as a comprehensive resource for researchers and practitioners, this systematic review provides insights into the current state of EvoRL and offers a guide for advancing its capabilities in the ever-evolving landscape of artificial intelligence., Comment: 18 pages, 2 figures

This paper addresses the study of novel constructions of variational analysis and generalized differentiation that are appropriate for characterizing robust stability properties of constrained set-valued mappings/multifunctions between Banach spaces important in optimization theory and its applications. Our tools of generalized differentiation revolves around the newly introduced concept of $\varepsilon$-regular normal cone to sets and associated coderivative notions for set-valued mappings. Based on these constructions, we establish several characterizations of the central stability notion known as the relative Lipschitz-like property of set-valued mappings in infinite dimensions. Applying a new version of the constrained extremal principle of variational analysis, we develop comprehensive sum and chain rules for our major constructions of conic contingent coderivatives for multifunctions between appropriate classes of Banach spaces., Comment: 26 pages. arXiv admin note: text overlap with arXiv:2212.02727

This paper proposes a mechanism to fine-tune convex approximations of probabilistic reachable sets (PRS) of uncertain dynamic systems. We consider the case of unbounded uncertainties, for which it may be impossible to find a bounded reachable set of the system. Instead, we turn to find a PRS that bounds system states with high confidence. Our data-driven approach builds on a kernel density estimator (KDE) accelerated by a fast Fourier transform (FFT), which is customized to model the uncertainties and obtain the PRS efficiently. However, the non-convex shape of the PRS can make it impractical for subsequent optimal designs. Motivated by this, we formulate a mixed integer nonlinear programming (MINLP) problem whose solution result is an optimal $n$ sided convex polygon that approximates the PRS. Leveraging this formulation, we propose a heuristic algorithm to find this convex set efficiently while ensuring accuracy. The algorithm is tested on comprehensive case studies that demonstrate its near-optimality, accuracy, efficiency, and robustness. The benefits of this work pave the way for promising applications to safety-critical, real-time motion planning of uncertain dynamic systems.

Artificial intelligence (AI)-empowered industrial fault diagnostics is important in ensuring the safe operation of industrial applications. Since complex industrial systems often involve multiple industrial plants (possibly belonging to different companies or subsidiaries) with sensitive data collected and stored in a distributed manner, collaborative fault diagnostic model training often needs to leverage federated learning (FL). As the scale of the industrial fault diagnostic models are often large and communication channels in such systems are often not exclusively used for FL model training, existing deployed FL model training frameworks cannot train such models efficiently across multiple institutions. In this paper, we report our experience developing and deploying the Federated Opportunistic Block Dropout (FEDOBD) approach for industrial fault diagnostic model training. By decomposing large-scale models into semantic blocks and enabling FL participants to opportunistically upload selected important blocks in a quantized manner, it significantly reduces the communication overhead while maintaining model performance. Since its deployment in ENN Group in February 2022, FEDOBD has served two coal chemical plants across two cities in China to build industrial fault prediction models. It helped the company reduce the training communication overhead by over 70% compared to its previous AI Engine, while maintaining model performance at over 85% test F1 score. To our knowledge, it is the first successfully deployed dropout-based FL approach.

The paper concerns foundations of sensitivity and stability analysis in optimization and related areas, being primarily addressed constrained systems. We consider general models, which are described by multifunctions between Banach spaces and concentrate on characterizing their well-posedness properties that revolve around Lipschitz stability and metric regularity relative to sets. Invoking tools of variational analysis and generalized differentiation, we introduce new robust notions of relative contingent coderivatives. The novel machinery of variational analysis leads us to establishing complete characterizations of the relative well-posedness properties and developing basic rules of variational calculus interrelated with the obtained characterizations of well-posedness. Most of the our results valid in general infinite-dimensional settings are also new in finite dimensions., Comment: 28 pages

Large-scale neural networks possess considerable expressive power. They are well-suited for complex learning tasks in industrial applications. However, large-scale models pose significant challenges for training under the current Federated Learning (FL) paradigm. Existing approaches for efficient FL training often leverage model parameter dropout. However, manipulating individual model parameters is not only inefficient in meaningfully reducing the communication overhead when training large-scale FL models, but may also be detrimental to the scaling efforts and model performance as shown by recent research. To address these issues, we propose the Federated Opportunistic Block Dropout (FedOBD) approach. The key novelty is that it decomposes large-scale models into semantic blocks so that FL participants can opportunistically upload quantized blocks, which are deemed to be significant towards training the model, to the FL server for aggregation. Extensive experiments evaluating FedOBD against four state-of-the-art approaches based on multiple real-world datasets show that it reduces the overall communication overhead by more than 88% compared to the best performing baseline approach, while achieving the highest test accuracy. To the best of our knowledge, FedOBD is the first approach to perform dropout on FL models at the block level rather than at the individual parameter level.

The probability prediction of multivariate time series is a notoriously challenging but practical task. On the one hand, the challenge is how to effectively capture the cross-series correlations between interacting time series, to achieve accurate distribution modeling. On the other hand, we should consider how to capture the contextual information within time series more accurately to model multivariate temporal dynamics of time series. In this work, we proposed a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF), where we integrate multi-scale attention and relative position information and the multivariate data distribution is represented by the conditioned normalizing flow. Additionally, compared with autoregressive modeling methods, our model avoids the influence of cumulative error and does not increase the time complexity. Extensive experiments demonstrate that our model achieves state-of-the-art performance on many popular multivariate datasets.

Recommender systems have been widely applied in different real-life scenarios to help us find useful information. In particular, Reinforcement Learning (RL) based recommender systems have become an emerging research topic in recent years, owing to the interactive nature and autonomous learning ability. Empirical results show that RL-based recommendation methods often surpass most of supervised learning methods. Nevertheless, there are various challenges of applying RL in recommender systems. To understand the challenges and relevant solutions, there should be a reference for researchers and practitioners working on RL-based recommender systems. To this end, we firstly provide a thorough overview, comparisons, and summarization of RL approaches applied in four typical recommendation scenarios, including interactive recommendation, conversational recommendatin, sequential recommendation, and explainable recommendation. Furthermore, we systematically analyze the challenges and relevant solutions on the basis of existing literature. Finally, under discussion for open issues of RL and its limitations of recommender systems, we highlight some potential research directions in this field., Comment: 21 pages, 4 figures, Accepted by TNNLS 2023

In this paper, we are interested in the existence of Pareto solutions to vector polynomial optimization problems over a basic closed semi-algebraic set. By invoking some powerful tools from real semi-algebraic geometry, we first introduce the concept called {\it tangency varieties}; then we establish connections of the Palais--Smale condition, Cerami condition, {\it M}-tameness, and properness related to the considered problem, in which the condition of Mangasarian--Fromovitz constraint qualification at infinity plays an essential role in deriving these connections. According to the obtained connections, we provide some sufficient conditions for existence of Pareto solutions to the problem in consideration, and we also give some examples to illustrate our main findings., Comment: 21 pages, 2 figures

Safety is a critical concern for the success of urban air mobility, especially in dynamic and uncertain environments. This paper proposes a path planning algorithm based on RRT in conjunction with chance constraints in the presence of uncertain obstacles. The chance-constrained formulation for Gaussian distributed obstacles is developed by converting the probabilistic constraints to deterministic constraints in terms of distribution parameters. The probabilistic feasible region at every time step can be established through the simulation of the system state and the evaluation of convex constraints. Through establishing chance-constrained RRT, the algorithm not only enjoys the benefits of sampling-based algorithms but also incorporates uncertainty into the formulation. Simulation results demonstrate that the planning for a trajectory connecting the starting and goal point in accordance with the requirement of probabilistic obstacle avoidance can be achieved by the utilization of this algorithm., Comment: 8 pages, AIAA conference article

The behaviors of deep neural networks (DNNs) are notoriously resistant to human interpretations. In this paper, we propose Hypergradient Data Relevance Analysis, or HYDRA, which interprets the predictions made by DNNs as effects of their training data. Existing approaches generally estimate data contributions around the final model parameters and ignore how the training data shape the optimization trajectory. By unrolling the hypergradient of test loss w.r.t. the weights of training data, HYDRA assesses the contribution of training data toward test data points throughout the training trajectory. In order to accelerate computation, we remove the Hessian from the calculation and prove that, under moderate conditions, the approximation error is bounded. Corroborating this theoretical claim, empirical results indicate the error is indeed small. In addition, we quantitatively demonstrate that HYDRA outperforms influence functions in accurately estimating data contribution and detecting noisy data labels. The source code is available at https://github.com/cyyever/aaai_hydra_8686.