Search

Traditional Markov Chain Monte Carlo sampling methods often struggle with sharp curvatures, intricate geometries, and multimodal distributions. Slice sampling can resolve local exploration inefficiency issues and Riemannian geometries help with sharp curvatures. Recent extensions enable slice sampling on Riemannian manifolds, but they are restricted to cases where geodesics are available in closed form. We propose a method that generalizes Hit-and-Run slice sampling to more general geometries tailored to the target distribution, by approximating geodesics as solutions to differential equations. Our approach enables exploration of regions with strong curvature and rapid transitions between modes in multimodal distributions. We demonstrate the advantages of the approach over challenging sampling problems.

In this paper, we investigate a challenging unsupervised domain adaptation setting -- unsupervised model adaptation. We aim to explore how to rely only on unlabeled target data to improve performance of an existing source prediction model on the target domain, since labeled source data may not be available in some real-world scenarios due to data privacy issues. For this purpose, we propose a new framework, which is referred to as collaborative class conditional generative adversarial net to bypass the dependence on the source data. Specifically, the prediction model is to be improved through generated target-style data, which provides more accurate guidance for the generator. As a result, the generator and the prediction model can collaborate with each other without source data. Furthermore, due to the lack of supervision from source data, we propose a weight constraint that encourages similarity to the source model. A clustering-based regularization is also introduced to produce more discriminative features in the target domain. Compared to conventional domain adaptation methods, our model achieves superior performance on multiple adaptation tasks with only unlabeled target data, which verifies its effectiveness in this challenging setting., Comment: accepted by CVPR2020

Existing code generation benchmarks for Large Language Models (LLMs) such as HumanEval and MBPP are designed to study LLMs' end-to-end performance, where the benchmarks feed a problem description in natural language as input and examine the generated code in specific programming languages. However, the evaluation scores revealed in this way provide a little hint as to the bottleneck of the code generation -- whether LLMs are struggling with their problem-solving capability or language-coding capability. To answer this question, we construct PseudoEval, a multilingual code generation benchmark that provides a solution written in pseudocode as input. By doing so, the bottleneck of code generation in various programming languages could be isolated and identified. Our study yields several interesting findings. For example, we identify that the bottleneck of LLMs in Python programming is problem-solving, while Rust is struggling relatively more in language-coding. Also, our study indicates that problem-solving capability may transfer across programming languages, while language-coding needs more language-specific effort, especially for undertrained programming languages. Finally, we release the pipeline of constructing PseudoEval to facilitate the extension to existing benchmarks. PseudoEval is available at: https://anonymous.4open.science/r/PseudocodeACL25-7B74.

Robot-assisted feeding systems enhance the independence of individuals with motor impairments and alleviate caregiver burden. While existing systems predominantly rely on software-based safety features to mitigate risks during unforeseen collisions, this study explores the use of a mechanical fail-safe to improve safety. We designed a breakaway utensil attachment that decouples forces exerted by the robot on the user when excessive forces occur. Finite element analysis (FEA) simulations were performed to predict failure points under various loading conditions, followed by experimental validation using 3D-printed attachments with variations in slot depth and wall loops. To facilitate testing, a drop test rig was developed and validated. Our results demonstrated a consistent failure point at the slot of the attachment, with a slot depth of 1 mm and three wall loops achieving failure at the target force of 65 N. Additionally, the parameters can be tailored to customize the breakaway force based on user-specific factors, such as comfort and pain tolerance. CAD files and utensil assembly instructions can be found here: https://tinyurl.com/rfa-utensil-attachment, Comment: 6 pages, 7 figures

The integration of AI techniques has become increasingly popular in software development, enhancing performance, usability, and the availability of intelligent features. With the rise of large language models (LLMs) and generative AI, developers now have access to a wealth of high-quality open-source models and APIs from closed-source providers, enabling easier experimentation and integration of LLMs into various systems. This has also opened new possibilities in mobile application (app) development, allowing for more personalized and intelligent apps. However, integrating LLM into mobile apps might present unique challenges for developers, particularly regarding mobile device constraints, API management, and code infrastructure. In this project, we constructed a comprehensive dataset of 149 LLM-enabled Android apps and conducted an exploratory analysis to understand how LLMs are deployed and used within mobile apps. This analysis highlights key characteristics of the dataset, prevalent integration strategies, and common challenges developers face. Our findings provide valuable insights for future research and tooling development aimed at enhancing LLM-enabled mobile apps.

Multiphase fluid dynamics, such as falling droplets and rising bubbles, are critical to many industrial applications. However, simulating these phenomena efficiently is challenging due to the complexity of instabilities, wave patterns, and bubble breakup. This paper investigates the potential of scientific machine learning (SciML) to model these dynamics using neural operators and foundation models. We apply sequence-to-sequence techniques on a comprehensive dataset generated from 11,000 simulations, comprising 1 million time snapshots, produced with a well-validated Lattice Boltzmann method (LBM) framework. The results demonstrate the ability of machine learning models to capture transient dynamics and intricate fluid interactions, paving the way for more accurate and computationally efficient SciML-based solvers for multiphase applications.

Accurate differentiation of pseudoprogression (PsP) from True Progression (TP) following radiotherapy (RT) in glioblastoma (GBM) patients is crucial for optimal treatment planning. However, this task remains challenging due to the overlapping imaging characteristics of PsP and TP. This study therefore proposes a multimodal deep-learning approach utilizing complementary information from routine anatomical MR images, clinical parameters, and RT treatment planning information for improved predictive accuracy. The approach utilizes a self-supervised Vision Transformer (ViT) to encode multi-sequence MR brain volumes to effectively capture both global and local context from the high dimensional input. The encoder is trained in a self-supervised upstream task on unlabeled glioma MRI datasets from the open BraTS2021, UPenn-GBM, and UCSF-PDGM datasets to generate compact, clinically relevant representations from FLAIR and T1 post-contrast sequences. These encoded MR inputs are then integrated with clinical data and RT treatment planning information through guided cross-modal attention, improving progression classification accuracy. This work was developed using two datasets from different centers: the Burdenko Glioblastoma Progression Dataset (n = 59) for training and validation, and the GlioCMV progression dataset from the University Hospital Erlangen (UKER) (n = 20) for testing. The proposed method achieved an AUC of 75.3%, outperforming the current state-of-the-art data-driven approaches. Importantly, the proposed approach relies on readily available anatomical MRI sequences, clinical data, and RT treatment planning information, enhancing its clinical feasibility. The proposed approach addresses the challenge of limited data availability for PsP and TP differentiation and could allow for improved clinical decision-making and optimized treatment plans for GBM patients.

Attention maps in neural models for NLP are appealing to explain the decision made by a model, hopefully emphasizing words that justify the decision. While many empirical studies hint that attention maps can provide such justification from the analysis of sound examples, only a few assess the plausibility of explanations based on attention maps, i.e., the usefulness of attention maps for humans to understand the decision. These studies furthermore focus on text classification. In this paper, we report on a preliminary assessment of attention maps in a sentence comparison task, namely natural language inference. We compare the cross-attention weights between two RNN encoders with human-based and heuristic-based annotations on the eSNLI corpus. We show that the heuristic reasonably correlates with human annotations and can thus facilitate evaluation of plausible explanations in sentence comparison tasks. Raw attention weights however remain only loosely related to a plausible explanation.

Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision. Empirical studies postulate that attention maps can be provided as an explanation for model output. However, it is still questionable to ask whether this explanation helps regular people to understand and accept the model output (the plausibility of the explanation). Recent studies show that attention weights in the RNN encoders are hardly plausible because they spread on input tokens. We thus propose 3 additional constraints to the learning objective function to improve the plausibility of the attention map: regularization to increase the attention weight sparsity, semi-supervision to supervise the map by a heuristic and supervision by human annotation. Results show that all techniques can improve the attention map plausibility at some level. We also observe that specific instructions for human annotation might have a negative effect on classification performance. Beyond the attention map, the result of experiments on text classification tasks also shows that no matter how the constraint brings the gain, the contextualization layer plays a crucial role in finding the right space for finding plausible tokens.

Blind face video restoration aims to restore high-fidelity details from videos subjected to complex and unknown degradations. This task poses a significant challenge of managing temporal heterogeneity while at the same time maintaining stable face attributes. In this paper, we introduce a Discrete Prior-based Temporal-Coherent content prediction transformer to address the challenge, and our model is referred to as DP-TempCoh. Specifically, we incorporate a spatial-temporal-aware content prediction module to synthesize high-quality content from discrete visual priors, conditioned on degraded video tokens. To further enhance the temporal coherence of the predicted content, a motion statistics modulation module is designed to adjust the content, based on discrete motion priors in terms of cross-frame mean and variance. As a result, the statistics of the predicted content can match with that of real videos over time. By performing extensive experiments, we verify the effectiveness of the design elements and demonstrate the superior performance of our DP-TempCoh in both synthetically and naturally degraded video restoration.

In 1965, Baxter established that a simple ring is either a field or that every one of its elements can be expressed as a sum of products of commutator pairs. In a recent paper, Gardella and Thiel demonstrated that every element in a noncommutative division ring can be represented as the sum of just two products of two commutators. They further posed the question of whether every element in a noncommutative division ring can be represented as the product of two commutators. In this paper, we affirmatively answer this question for skew Laurent series division rings over fields.

While ridges in the scalogram, determined by the squared modulus of analytic wavelet transform (AWT), have been widely applied in time series analysis and time-frequency analysis, their behavior in noisy environments remains underexplored. We fill in this gap in this paper. We define ridges as paths formed by local maximizers of the scalogram along the scale axis, and analyze their properties when the signal is contaminated by stationary Gaussian noise. In addition to establishing several key properties of the AWT for random processes, we investigate the probabilistic characteristics of the resulting random ridge points in the scalogram. Specifically, we establish the uniqueness property of the ridge point at individual time instances and prove the upper hemicontinuity of the set of ridge points. Furthermore, we derive bounds on the probability that the deviation between the ridge points of noisy and clean signals exceeds a specified threshold. These bounds are expressed in terms of constants related to the signal-to-noise ratio and apply when the signal satisfies the adaptive harmonic model and is corrupted by a stationary Gaussian process. To achieve these results, we derive maximal inequalities for the complex modulus of nonstationary Gaussian processes, leveraging classical tools such as the Borell-TIS inequality and Dudley's theorem, which might be of independent interest.

This paper presents an incomplete Octree mesh implementation of the Shifted Boundary Method (Octree-SBM) for multiphysics simulations of coupled flow and heat transfer. Specifically, a semi-implicit formulation of the thermal Navier-Stokes equations is used to accelerate the simulations while maintaining accuracy. The SBM enables precise enforcement of field and derivative boundary conditions on cut (intercepted) elements, allowing for accurate flux calculations near complex geometries, when using non-boundary fitted meshes. Both Dirichlet and Neumann boundary conditions are implemented within the SBM framework, with results demonstrating that the SBM ensures precise enforcement of Neumann boundary conditions on Octree-based meshes. We illustrate this approach by simulating flows across different regimes, spanning several orders of magnitude in both the Rayleigh number ($Ra \sim 10^3$--$10^9$) and the Reynolds number ($Re \sim 10^0$--$10^4$), and covering the laminar, transitional, and turbulent flow regimes. Coupled thermal-flow phenomena and their statistics across all these regimes are accurately captured without any additional numerical treatments, beyond a Residual-based Variational Multiscale formulation (RB-VMS). This approach offers a reliable and efficient solution for complex geometries, boundary conditions and flow regimes in computational multiphysics simulations.

Many applications like subseismic fault modeling, fractured reservoir modeling and interpretation/validation of fault connectivity involve the solution to an elliptic boundary value problem in a background medium perturbed by the presence of cracks that take the form of one or many pieces of surface (with boundary). When the background medium can be considered as homogeneous, boundary integral equations appear as a method of choice for the numerical solution to fractures problems. With such an approach, the problem is reformulated as a fully non-local equation posed at the surface of cracks. Discretization of boundary integral resulting in the so-called Boundary Element Method (BEM) leads to densely populated matrices due to the full non-locality of the operators under consideration. After the discretization process, geologists are faced with a system of equations that turns out difficult to solve numerically. Many empirical algorithms have been proposed by geologists to solve this system of equations. Unfortunately, none of them is guaranteed to converge in theory (in particular when faults (fractures) intersect each other forming a geometrically highly irregular structure). In practice, none of them appears to be either robust or efficient. We investigate another approach, referred to as interior point methods, for which convergence can be ensured (even if faults are too close). Interior point methods have proved their efficiency in a wide variety of domains, most notably for linear programming. Here, even though we do not have any optimization problem, we can adapt ideas from interior point methods for the numerical resolution of the system considered. The numerical results obtained demonstrate computational efficiency and accuracy, highlighting the robustness and effectiveness of the implemented methods.

Assume that $\mathbb F$ is an algebraically closed field and fix a nonzero scalar $q\in \mathbb F$ with $q^4\not=1$. The universal Askey--Wilson algebra $\triangle_q$ is a unital associative algebra over $\mathbb F$ defined by generators and relations. The generators are $A,B,C$ and the relations assert that each of \begin{gather*} A+\frac{qBC-q^{-1}CB}{q^2-q^{-2}}, \qquad B+\frac{qCA-q^{-1}AC}{q^2-q^{-2}}, \qquad C+\frac{qAB-q^{-1}BA}{q^2-q^{-2}} \end{gather*} commutes with $A,B,C$. The Verma $\triangle_q$-modules are a family of infinite-dimensional $\triangle_q$-modules with marginal weights. Under the condition that $q$ is not a root of unity, it was shown that every finite-dimensional irreducible $\triangle_q$-module has a marginal weight and is isomorphic to a quotient of a Verma $\triangle_q$-module. Assume that $q$ is a root of unity. We prove that every finite-dimensional irreducible $\triangle_q$-module with a marginal weight is isomorphic to a quotient of a Verma $\triangle_q$-module. Properly speaking, two natural families of finite-dimensional quotients of Verma $\triangle_q$-modules contain all finite-dimensional irreducible $\triangle_q$-modules with marginal weights up to isomorphism. Furthermore, we classify the finite-dimensional irreducible $\triangle_q$-modules with marginal weights up to isomorphism.

This paper investigates the performance of a subclass of exponential integrators, specifically explicit exponential Runge--Kutta methods. It is well known that third-order methods can suffer from order reduction when applied to linearized problems involving unbounded and non-commuting operators. In this work, we consider a fourth-stage third-order Runge--Kutta method, which successfully achieves the expected order of accuracy and avoids order reduction, as long as all required order conditions are satisfied. The convergence analysis is carried out under the assumption of higher regularity for the initial data. Numerical experiments are provided to validate the theoretical results., Comment: 16 pages, 2 figures

This study establishes the consistency of Bayesian adaptive testing methods under the Rasch model, addressing a gap in the literature on their large-sample guarantees. Although Bayesian approaches are recognized for their finite-sample performance and capability to circumvent issues such as the cold-start problem; however, rigorous proofs of their asymptotic properties, particularly in non-i.i.d. structures, remain lacking. We derive conditions under which the posterior distributions of latent traits converge to the true values for a sequence of given items, and demonstrate that Bayesian estimators remain robust under the mis-specification of the prior. Our analysis then extends to adaptive item selection methods in which items are chosen endogenously during the test. Additionally, we develop a Bayesian decision-theoretical framework for the item selection problem and propose a novel selection that aligns the test process with optimal estimator performance. These theoretical results provide a foundation for Bayesian methods in adaptive testing, complementing prior evidence of their finite-sample advantages.

The bullwhip study has received a lot of attention in the literature, but with conflicting results, especially in the context of data aggregation. In this paper, we investigate three widely studied factors in bullwhip measurement: time aggregation, product aggregation, and seasonality. In time aggregation, we decompose the variance into two components: the expectation of the subset variances and the variance of subset expectations, thus decomposing the bullwhip ratio into four components to explore the underlying mechanism of time aggregation. In product aggregation, the bullwhip ratio is analyzed in the context of products with either uncorrelated or correlated demands and orders. Seasonality is also examined to study its effect on the bullwhip ratio. Our key findings are: (a) Time aggregation can increase, decrease, or maintain the bullwhip ratio in different scenarios. (b) Aggregated bullwhip ratio of uncorrelated products is a weighted average of bullwhip ratios from individual products, with corresponding demand variance as the weights. However, aggregated bullwhip ratio of correlated products could break the boundaries. (c) Seasonality can be considered as a standalone product with a bullwhip ratio of one, which can drive the overall bullwhip ratio closer to one.

The p-type point-contact germanium (pPCGe) detectors have been widely adopted in searches for low energy physics events such as neutrinos and dark matter. This is due to their enhanced capabilities of background rejection, sensitivity at energies as low as the sub-keV range and particularly fine energy resolution. Nonetheless, the pPCGe is subject to irregular behaviour caused by surface effects for events near the passivated surface. These surface events can, in general, be distinguished from events that occur in the germanium crystal bulk by its slower pulse rise time. Unfortunately, the rise-time spectra of bulk and surface events starts to convolve with each other at sub-keV energies. In this work, we propose a novel method based on cross-correlation shape-matching combined with a low-pass filter to constrain the initial parameter estimates of the signal pulse. This improvement at the lowest level leads to a 50% reduction in computation time and refinements in the rise-time resolution, which will, in the end, enhance the overall analysis. To evaluate the performance of the method, we simulate artificial pulses that resembles bulk and surface pulses by using a programmable pulse generator module (pulser). The pulser-generated pulses are then used to examine the pulse behaviours at near-threshold energies, suggesting a roughly 70% background-leakage reduction in the bulk spectrum. Finally, the method is tested on data collected from the TEXONO experiment, where the results are consistent with our observations in pulser and demonstrated the possibility of lowering the analysis threshold by at least 10eV.

Data contamination presents a critical barrier preventing widespread industrial adoption of advanced software engineering techniques that leverage code language models (CLMs). This phenomenon occurs when evaluation data inadvertently overlaps with the public code repositories used to train CLMs, severely undermining the credibility of performance evaluations. For software companies considering the integration of CLM-based techniques into their development pipeline, this uncertainty about true performance metrics poses an unacceptable business risk. Code refactoring, which comprises code restructuring and variable renaming, has emerged as a promising measure to mitigate data contamination. It provides a practical alternative to the resource-intensive process of building contamination-free evaluation datasets, which would require companies to collect, clean, and label code created after the CLMs' training cutoff dates. However, the lack of automated code refactoring tools and scientifically validated refactoring techniques has hampered widespread industrial implementation. To bridge the gap, this paper presents the first systematic study to examine the efficacy of code refactoring operators at multiple scales (method-level, class-level, and cross-class level) and in different programming languages. In particular, we develop an open-sourced toolkit, CODECLEANER, which includes 11 operators for Python, with nine method-level, one class-level, and one cross-class-level operator. A drop of 65% overlap ratio is found when applying all operators in CODECLEANER, demonstrating their effectiveness in addressing data contamination. Additionally, we migrate four operators to Java, showing their generalizability to another language. We make CODECLEANER online available to facilitate further studies on mitigating CLM data contamination.

Sleep staging is a challenging task, typically manually performed by sleep technologists based on electroencephalogram and other biosignals of patients taken during overnight sleep studies. Recent work aims to leverage automated algorithms to perform sleep staging not based on electroencephalogram signals, but rather based on the airflow signals of subjects. Prior work uses ideas from topological data analysis (TDA), specifically Hermite function expansions of persistence curves (HEPC) to featurize airflow signals. However, finite order HEPC captures only partial information. In this work, we propose Fourier approximations of persistence curves (FAPC), and use this technique to perform sleep staging based on airflow signals. We analyze performance using an XGBoost model on 1155 pediatric sleep studies taken from the Nationwide Children's Hospital Sleep DataBank (NCHSDB), and find that FAPC methods provide complimentary information to HEPC methods alone, leading to a 4.9% increase in performance over baseline methods.

Using data from professional bouldering competitions from 2008 to 2022, we train a logistic regression to predict climber results and measure climber skill. However, this approach is limited, as a single numeric coefficient per climber cannot adequately capture the intricacies of climbers' varying strengths and weaknesses in different boulder problems. For example, some climbers might prefer more static, technical routes while other climbers may specialize in powerful, dynamic problems. To this end, we apply Probabilistic Matrix Factorization (PMF), a framework commonly used in recommender systems, to represent the unique characteristics of climbers and problems with latent, multi-dimensional vectors. In this framework, a climber's performance on a given problem is predicted by taking the dot product of the corresponding climber vector and problem vectors. PMF effectively handles sparse datasets, such as our dataset where only a subset of climbers attempt each particular problem, by extrapolating patterns from similar climbers. We contrast the empirical performance of PMF to the logistic regression approach and investigate the multivariate representations produced by PMF to gain insights into climber characteristics. Our results show that the multivariate PMF representations improve predictive performance of professional bouldering competitions by capturing both the overall strength of climbers and their specialized skill sets. We provide our code open-source at https://github.com/baronet2/boulder2vec.

Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their in-context learning (ICL) capacity, allowing them to solve new tasks using only task-specific prompts without further fine-tuning. On the other hand, existing empirical and theoretical studies also show that there is a linear regularity of the multi-concept encoded semantic representation behind transformer-based LLMs. However, existing theoretical work fail to build up an understanding of the connection between this regularity and the innovative power of ICL. Additionally, prior work often focuses on simplified, unrealistic scenarios involving linear transformers or unrealistic loss functions, and they achieve only linear or sub-linear convergence rates. In contrast, this work provides a fine-grained mathematical analysis to show how transformers leverage the multi-concept semantics of words to enable powerful ICL and excellent out-of-distribution ICL abilities, offering insights into how transformers innovate solutions for certain unseen tasks encoded with multiple cross-concept semantics. Inspired by empirical studies on the linear latent geometry of LLMs, the analysis is based on a concept-based low-noise sparse coding prompt model. Leveraging advanced techniques, this work showcases the exponential 0-1 loss convergence over the highly non-convex training dynamics, which pioneeringly incorporates the challenges of softmax self-attention, ReLU-activated MLPs, and cross-entropy loss. Empirical simulations corroborate the theoretical findings., Comment: Accepted by the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

We extend the shifted boundary method (SBM) to the simulation of incompressible fluid flow using immersed octree meshes. Previous work on SBM for fluid flow primarily utilized two- or three-dimensional unstructured tetrahedral grids. Recently, octree grids have become an essential component of immersed CFD solvers, and this work addresses this gap and the associated computational challenges. We leverage an optimal (approximate) surrogate boundary constructed efficiently on incomplete and adaptive octree meshes. The resulting framework enables the simulation of the incompressible Navier-Stokes equations in complex geometries without requiring boundary-fitted grids. Simulations of benchmark tests in two and three dimensions demonstrate that the Octree-SBM framework is a robust, accurate, and efficient approach to simulating fluid dynamics problems with complex geometries.

In Markov decision processes (MDPs), quantile risk measures such as Value-at-Risk are a standard metric for modeling RL agents' preferences for certain outcomes. This paper proposes a new Q-learning algorithm for quantile optimization in MDPs with strong convergence and performance guarantees. The algorithm leverages a new, simple dynamic program (DP) decomposition for quantile MDPs. Compared with prior work, our DP decomposition requires neither known transition probabilities nor solving complex saddle point equations and serves as a suitable foundation for other model-free RL algorithms. Our numerical results in tabular domains show that our Q-learning algorithm converges to its DP variant and outperforms earlier algorithms.

In this paper, we consider the application of exponential integrators to problems that are advection dominated, either on the entire or on a subset of the domain. In this context, we compare Leja and Krylov based methods to compute the action of exponential and related matrix functions. We set up a performance model by counting the different operations needed to implement the considered algorithms. This model assumes that the evaluation of the right-hand side is memory bound and allows us to evaluate performance in a hardware independent way. We find that exponential integrators perform comparably to explicit Runge-Kutta schemes for problems that are advection dominated in the entire domain. Moreover, they are able to outperform explicit methods in situations where small parts of the domain are diffusion dominated. We generally observe that Leja based methods outperform Krylov iterations in the problems considered. This is in particular true if computing inner products is expensive.

In this paper, we propose a new approach to train deep learning models using game theory concepts including Generative Adversarial Networks (GANs) and Adversarial Training (AT) where we deploy a double-oracle framework using best response oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. The same concept can be applied to AT with attacker and classifier as players. Training these models is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as training algorithms for both GAN and AT have a large-scale strategy space. Extending our preliminary model DO-GAN, we propose the methods to apply the double oracle framework concept to Adversarial Neural Architecture Search (NAS for GAN) and Adversarial Training (NAS for AT) algorithms. We first generalize the players' strategies as the trained models of generator and discriminator from the best response oracles. We then compute the meta-strategies using a linear program. For scalability of the framework where multiple network models of best responses are stored in the memory, we prune the weakly-dominated players' strategies to keep the oracles from becoming intractable. Finally, we conduct experiments on MNIST, CIFAR-10 and TinyImageNet for DONAS-GAN. We also evaluate the robustness under FGSM and PGD attacks on CIFAR-10, SVHN and TinyImageNet for DONAS-AT. We show that all our variants have significant improvements in both subjective qualitative evaluation and quantitative metrics, compared with their respective base architectures.

The anticipation of human behavior is a crucial capability for robots to interact with humans safely and efficiently. We employ a smart edge sensor network to provide global observations along with future predictions and goal information to integrate anticipatory behavior for the control of a mobile manipulation robot. We present approaches to anticipate human behavior in the context of safe navigation and a collaborative mobile manipulation task. First, we anticipate human motion by employing projections of human trajectories from smart edge sensor network observations into the planning map of a mobile robot. Second, we anticipate human intentions in a collaborative furniture-carrying task to achieve a given goal. Our experiments indicate that anticipating human behavior allows for safer navigation and more efficient collaboration. Finally, we showcase an integrated system that anticipates human behavior and collaborates with a human to achieve a target room layout, including the placement of tables and chairs.

Optimization in the Bures-Wasserstein space has been gaining popularity in the machine learning community since it draws connections between variational inference and Wasserstein gradient flows. The variational inference objective function of Kullback-Leibler divergence can be written as the sum of the negative entropy and the potential energy, making forward-backward Euler the method of choice. Notably, the backward step admits a closed-form solution in this case, facilitating the practicality of the scheme. However, the forward step is not exact since the Bures-Wasserstein gradient of the potential energy involves "intractable" expectations. Recent approaches propose using the Monte Carlo method -- in practice a single-sample estimator -- to approximate these terms, resulting in high variance and poor performance. We propose a novel variance-reduced estimator based on the principle of control variates. We theoretically show that this estimator has a smaller variance than the Monte-Carlo estimator in scenarios of interest. We also prove that variance reduction helps improve the optimization bounds of the current analysis. We demonstrate that the proposed estimator gains order-of-magnitude improvements over the previous Bures-Wasserstein methods.

Recent research has focused on the risks associated with poor sitting posture and the impact of sitting on biological parameters, such as heart rate because prolonged sitting is common across all ages and professions. In this work, we propose a novel approach that can display simultaneously posture and heart rate in real-time. In this device, pressure sensors are embedded into a flexible separate cushion easily put on any chair to provide sitting behaviours and a smartwatch-like PPG module is worn on the user's wrist. Regarding posture classification, pressure figures of ten pressure sensors under the seat bottom are inputs of four machine learning models, giving a high accuracy of 99 per cent. Besides, the Electrocardiography recording module is illustrated with the same results as a commercial device called DFRobot. Another advantage of this smart chair is that it not only simultaneously displays both sitting postures and heart rates on external devices like laptops, mobile phones, or televisions through microcontrollers but also offers the relationship between them to help people adjust their sitting behaviours, avoiding influencing heart rate. The smart chair is expected to be useful equipment for people with a sedentary lifestyle, especially office workers.

Nonlinear parabolic equations are central to numerous applications in science and engineering, posing significant challenges for analytical solutions and necessitating efficient numerical methods. Exponential integrators have recently gained attention for handling stiff differential equations. This paper explores exponential Runge--Kutta methods for solving such equations, focusing on the simplified form $u^{\prime}(t)+A u(t)=B u(t)$, where $A$ generates an analytic semigroup and $B$ is relatively bounded with respect to $A$. By treating $A$ exactly and $B$ explicitly, we derive error bounds for exponential Runge--Kutta methods up to third order. Our analysis shows that these methods maintain their order under mild regularity conditions on the initial data $u_0$, while also addressing the phenomenon of order reduction in higher-order methods. Through a careful convergence analysis and numerical investigations, this study provides a comprehensive understanding of the applicability and limitations of exponential Runge--Kutta methods in solving linear parabolic equations involving two unbounded and non-commuting operators., Comment: 25 pages, 4 figures

Simulating fluid flow around arbitrary shapes is key to solving various engineering problems. However, simulating flow physics across complex geometries remains numerically challenging and computationally resource-intensive, particularly when using conventional PDE solvers. Machine learning methods offer attractive opportunities to create fast and adaptable PDE solvers. However, benchmark datasets to measure the performance of such methods are scarce, especially for flow physics across complex geometries. We introduce FlowBench, a dataset for neural simulators with over 10K samples, which is currently larger than any publicly available flow physics dataset. FlowBench contains flow simulation data across complex geometries (\textit{parametric vs. non-parametric}), spanning a range of flow conditions (\textit{Reynolds number and Grashoff number}), capturing a diverse array of flow phenomena (\textit{steady vs. transient; forced vs. free convection}), and for both 2D and 3D. FlowBench contains over 10K data samples, with each sample the outcome of a fully resolved, direct numerical simulation using a well-validated simulator framework designed for modeling transport phenomena in complex geometries. For each sample, we include velocity, pressure, and temperature field data at 3 different resolutions and several summary statistics features of engineering relevance (such as coefficients of lift and drag, and Nusselt numbers). %Additionally, we include masks and signed distance fields for each shape. We envision that FlowBench will enable evaluating the interplay between complex geometry, coupled flow phenomena, and data sufficiency on the performance of current, and future, neural PDE solvers. We enumerate several evaluation metrics to help rank order the performance of neural PDE solvers. We benchmark the performance of several baseline methods including FNO, CNO, WNO, and DeepONet.

USB-based attacks have increased in complexity in recent years. Modern attacks incorporate a wide range of attack vectors, from social engineering to signal injection. The security community is addressing these challenges using a growing set of fragmented defenses. Regardless of the vector of a USB-based attack, the most important risks concerning most people and enterprises are service crashes and data loss. The host OS manages USB peripherals, and malicious USB peripherals, such as those infected with BadUSB, can crash a service or steal data from the OS. Although USB firewalls have been proposed to thwart malicious USB peripherals, such as USBFilter and USBGuard, they cannot prevent real-world intrusions. This paper focuses on building a security framework called USBIPS within OSs to defend against malicious USB peripherals. This includes major efforts to explore the nature of malicious behavior and build persistent protection from USB-based intrusions. We first present a behavior-based detection mechanism focusing on attacks integrated into USB peripherals. We then introduce the novel idea of an allowlisting-based method for USB access control. We finally develop endpoint detection and response system to build the first generic security framework that thwarts USB-based intrusion. Within a centralized threat analysis framework, it provides persistent protection and may detect unknown malicious behavior. By addressing key security and performance challenges, these efforts help modern OSs against attacks from untrusted USB peripherals., Comment: Under review by Computer Standards & Interfaces

We study a variation of facility location problems (FLPs) that aims to improve the accessibility of agents to the facility within the context of mechanism design without money. In such a variation, agents have preferences on the ideal locations of the facility on a real line, and the facility's location is fixed in advance where (re)locating the facility is not possible due to various constraints (e.g., limited space and construction costs). To improve the accessibility of agents to facilities, existing mechanism design literature in FLPs has proposed to structurally modify the real line (e.g., by adding a new interval) or provide shuttle services between two points when structural modifications are not possible. In this paper, we focus on the latter approach and propose to construct an accessibility range to extend the accessibility of the facility. In the range, agents can receive accommodations (e.g., school buses, campus shuttles, or pickup services) to help reach the facility. Therefore, the cost of each agent is the distance from their ideal location to the facility (possibility) through the range. We focus on designing strategyproof mechanisms that elicit true ideal locations from the agents and construct accessibility ranges (intervals) to approximately minimize the social cost or the maximum cost of agents. For both social and maximum costs, we design group strategyproof mechanisms with asymptotically tight bounds on the approximation ratios., Comment: To appear in ECAI 2024

Beam hopping (BH) is a satellite communications technique in which sets of beams are sequentially illuminated over a defined time interval. Geographically varying the duty cycle of satellite transmission allows for reduced resource wastage as satellite capacity is matched to non-uniform user demands. Total feasible active beam combinations is given by $2^n$ for $n$ beams. With in service satellite systems operating in excess of 100 beams, complete enumeration of optimum illumination patterns is not tractable. Developing efficient optimization methods which minimize resource wastage is essential to realising the benefits of modern BH systems. We present a computationally efficient pattern generation method which uses the binary logarithm to decompose beam demands into common powers of two. This method is shown to produce feasible patterns within 0.047 and 0.31 seconds for systems using 49 and 132 beams respectively and within 19.109 seconds for a 1085 beam system. When averaged across all testing configurations, this method reduced capacity error by 94% compared to a conventional even data distribution. To facilitate algorithm comparison, two integer linear programming formulations are developed. Even though they can only solve problems of modest sizes to proven optimality, they provide valuable insights in the optimality gap for our proposed heuristic approach.

Nash equilibrium (NE) is a widely adopted solution concept in game theory due to its stability property. However, we observe that the NE strategy might not always yield the best results, especially against opponents who do not adhere to NE strategies. Based on this observation, we pose a new game-solving question: Can we learn a model that can exploit any, even NE, opponent to maximize their own utility? In this work, we make the first attempt to investigate this problem through in-context learning. Specifically, we introduce a novel method, In-Context Exploiter (ICE), to train a single model that can act as any player in the game and adaptively exploit opponents entirely by in-context learning. Our ICE algorithm involves generating diverse opponent strategies, collecting interactive history training data by a reinforcement learning algorithm, and training a transformer-based agent within a well-designed curriculum learning framework. Finally, comprehensive experimental results validate the effectiveness of our ICE algorithm, showcasing its in-context learning ability to exploit any unknown opponent, thereby positively answering our initial game-solving question.

Substance use is a global issue that negatively impacts millions of persons who use drugs (PWUDs). In practice, identifying vulnerable PWUDs for efficient allocation of appropriate resources is challenging due to their complex use patterns (e.g., their tendency to change usage within months) and the high acquisition costs for collecting PWUD-focused substance use data. Thus, there has been a paucity of machine learning models for accurately predicting short-term substance use behaviors of PWUDs. In this paper, using longitudinal survey data of 258 PWUDs in the U.S. Great Plains collected by our team, we design a novel GAN that deals with high-dimensional low-sample-size tabular data and survey skip logic to augment existing data to improve classification models' prediction on (A) whether the PWUDs would increase usage and (B) at which ordinal frequency they would use a particular drug within the next 12 months. Our evaluation results show that, when trained on augmented data from our proposed GAN, the classification models improve their predictive performance (AUROC) by up to 13.4% in Problem (A) and 15.8% in Problem (B) for usage of marijuana, meth, amphetamines, and cocaine, which outperform state-of-the-art generative models., Comment: Accepted in IJCAI 2024

The utilization of face masks is an essential healthcare measure, particularly during times of pandemics, yet it can present challenges in communication in our daily lives. To address this problem, we propose a novel approach known as the human-in-the-loop StarGAN (HL-StarGAN) face-masked speech enhancement method. HL-StarGAN comprises discriminator, classifier, metric assessment predictor, and generator that leverages an attention mechanism. The metric assessment predictor, referred to as MaskQSS, incorporates human participants in its development and serves as a "human-in-the-loop" module during the learning process of HL-StarGAN. The overall HL-StarGAN model was trained using an unsupervised learning strategy that simultaneously focuses on the reconstruction of the original clean speech and the optimization of human perception. To implement HL-StarGAN, we curated a face-masked speech database named "FMVD," which comprises recordings from 34 speakers in three distinct face-masked scenarios and a clean condition. We conducted subjective and objective tests on the proposed HL-StarGAN using this database. The outcomes of the test results are as follows: (1) MaskQSS successfully predicted the quality scores of face mask voices, outperforming several existing speech assessment methods. (2) The integration of the MaskQSS predictor enhanced the ability of HL-StarGAN to transform face mask voices into high-quality speech; this enhancement is evident in both objective and subjective tests, outperforming conventional StarGAN and CycleGAN-based systems., Comment: face-mask speech enhancement, generative adversarial networks, StarGAN, human-in-the-loop, unsupervised learning

This paper introduces a method for zero-shot video restoration using pre-trained image restoration diffusion models. Traditional video restoration methods often need retraining for different settings and struggle with limited generalization across various degradation types and datasets. Our approach uses a hierarchical token merging strategy for keyframes and local frames, combined with a hybrid correspondence mechanism that blends optical flow and feature-based nearest neighbor matching (latent merging). We show that our method not only achieves top performance in zero-shot video restoration but also significantly surpasses trained models in generalization across diverse datasets and extreme degradations (8$\times$ super-resolution and high-standard deviation video denoising). We present evidence through quantitative metrics and visual comparisons on various challenging datasets. Additionally, our technique works with any 2D restoration diffusion model, offering a versatile and powerful tool for video enhancement tasks without extensive retraining. This research leads to more efficient and widely applicable video restoration technologies, supporting advancements in fields that require high-quality video output. See our project page for video results and source code at https://jimmycv07.github.io/DiffIR2VR_web/., Comment: Project page: https://jimmycv07.github.io/DiffIR2VR_web/