Related papers: Rare event modeling with self-regularized normaliz…

Urban flood emergency response increasingly relies on infrastructure impact forecasts rather than hazard variables alone. However, real-time predictions are unreliable due to biased rainfall, incomplete flood knowledge, and sparse…

Action-constrained reinforcement learning (ACRL) is a popular approach for solving safety-critical and resource-allocation related decision making problems. A major challenge in ACRL is to ensure agent taking a valid action satisfying…

While machine learning systems show high success rate in many complex tasks, research shows they can also fail in very unexpected situations. Rise of machine learning products in safety-critical industries cause an increase in attention in…

Multi-robot target tracking is a fundamental problem that requires coordinated monitoring of dynamic entities in applications such as precision agriculture, environmental monitoring, disaster response, and security surveillance. While…

Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy…

Deep neural networks, when optimized with sufficient data, provide accurate representations of high-dimensional functions; in contrast, function approximation techniques that have predominated in scientific computing do not scale well with…

Super-resolution is an ill-posed problem, since it allows for multiple predictions for a given low-resolution image. This fundamental fact is largely ignored by state-of-the-art deep learning based approaches. These methods instead train a…

Modern big-data systems generate massive, heterogeneous, and geographically dispersed streams that are large-scale and privacy-sensitive, making centralization challenging. While federated learning (FL) provides a privacy-enhancing training…

Many modern nonlinear control methods aim to endow systems with guaranteed properties, such as stability or safety, and have been successfully applied to the domain of robotics. However, model uncertainty remains a persistent challenge,…

Planning is a critical component of end-to-end autonomous driving. However, prevailing imitation learning methods often suffer from mode collapse, failing to produce diverse trajectory hypotheses. Meanwhile, existing generative approaches…

Deep learning has enjoyed much recent success, and applying state-of-the-art model learning methods to controls is an exciting prospect. However, there is a strong reluctance to use these methods on safety-critical systems, which have…

Machine learning (ML) algorithms are remarkably good at approximating complex non-linear relationships. Most ML training processes, however, are designed to deliver ML tools with good average performance, but do not offer any guarantees…

Wireless federated learning (WFL) suffers from heterogeneity prevailing in the data distributions, computing powers, and channel conditions of participating devices. This paper presents a new Federated Learning with Adjusted leaRning ratE…

Machine fault diagnosis (FD) is a critical task for predictive maintenance, enabling early fault detection and preventing unexpected failures. Despite its importance, existing FD models are operation-specific with limited generalization…

Breaking safety constraints in control systems can lead to potential risks, resulting in unexpected costs or catastrophic damage. Nevertheless, uncertainty is ubiquitous, even among similar tasks. In this paper, we develop a novel adaptive…

Failure probability estimation problem is an crucial task in engineering. In this work we consider this problem in the situation that the underlying computer models are extremely expensive, which often arises in the practice, and in this…

Federated learning (FL) facilitates collaborative model training among multiple clients while preserving data privacy, often resulting in enhanced performance compared to models trained by individual clients. However, factors such as…

Distributed systems frequently encounter consistency violation faults (cvfs), where nodes operate on outdated or inaccurate data, adversely affecting convergence and overall system performance. This study presents a machine learning-based…

Reinforcement learning (RL) has proven to be particularly effective in solving complex decision-making problems for a wide range of applications. Safe reinforcement learning refers to a class of constrained problems where the constraint…

The AC Optimal Power Flow (AC-OPF) problem is central to power system operation but challenging to solve efficiently due to its nonconvex and nonlinear nature. Neural networks (NNs) offer fast surrogates, yet their black-box behavior raises…