相关论文: From Raw Data to Safety: Reducing Conservatism by …

Safe Reinforcement Learning (SRL) aims to realize a safe learning process for Deep Reinforcement Learning (DRL) algorithms by incorporating safety constraints. However, the efficacy of SRL approaches often relies on accurate function…

The last two years have seen a rapid growth in concerns around the safety of large language models (LLMs). Researchers and practitioners have met these concerns by creating an abundance of datasets for evaluating and improving LLM safety.…

This paper presents LDP-Fed, a novel federated learning system with a formal privacy guarantee using local differential privacy (LDP). Existing LDP protocols are developed primarily to ensure data privacy in the collection of single…

With the rapid expansion of edge devices, such as IoT devices, where crucial data needed for machine learning applications is generated, it becomes essential to promote their participation in privacy-preserving Federated Learning (FL)…

We consider the problem of navigating a nonlinear dynamical system from some initial set to some target set while avoiding collision with an unsafe set. We extend the concept of density function to control density function (CDF) for solving…

Learning-based approaches for constructing Control Barrier Functions (CBFs) are increasingly being explored for safety-critical control systems. However, these methods typically require complete retraining when applied to unseen…

Feature selection helps reduce data acquisition costs in ML, but the standard approach is to train models with static feature subsets. Here, we consider the dynamic feature selection (DFS) problem where a model sequentially queries features…

Federated Learning (FL) has become a widely used approach for training machine learning models on decentralized data, addressing the significant privacy concerns associated with traditional centralized methods. However, the efficiency of FL…

Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a…

Federated Learning (FL) enables decentralized machine learning while preserving data privacy. This paper proposes a novel client selection framework that integrates differential privacy and fault tolerance. The adaptive client selection…

Designing controllers that accomplish tasks while guaranteeing safety constraints remains a significant challenge. We often want an agent to perform well in a nominal task, such as environment exploration, while ensuring it can avoid unsafe…

In many robotic applications, it is crucial to maintain a belief about the state of a system, which serves as input for planning and decision making and provides feedback during task execution. Bayesian Filtering algorithms address this…

This paper studies satisfaction of temporal properties on unknown stochastic processes that have continuous state spaces. We show how reinforcement learning (RL) can be applied for computing policies that are finite-memory and deterministic…

Latent representations are critical for the performance and robustness of machine learning models, as they encode the essential features of data in a compact and informative manner. However, in vision tasks, these representations are often…

This paper develops a data-driven stabilization method for continuous-time linear time-invariant systems with theoretical guarantees and no need for signal derivatives. The framework, based on linear matrix inequalities (LMIs), is…

With rapid advancement and increasing accessibility of LLMs, fine-tuning aligned models has become a critical step for adapting them to real-world applications, which makes the safety of this fine-tuning process more important than ever.…

Designing safety-critical control for robotic manipulators is challenging, especially in a cluttered environment. First, the actual trajectory of a manipulator might deviate from the planned one due to the complex collision environments and…

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality…

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected return using a given static dataset of transitions. However, offline RL faces the distribution shift problem. The policy constraint offline RL method is…

We consider the problem of direct data-driven predictive control for unknown stochastic linear time-invariant (LTI) systems with partial state observation. Building upon our previous research on data-driven stochastic control, this paper…