10 papers · 1 filter
Towards Identifiable Representations under Misspecified Structure
Yuke Li, Yujia Zheng, Ziyi Chen +2
The presence of noise that depends on the latent variables poses a fundamental challenge to identifiability. Existing results rely on conditional independence among the observation…
Optimal and Order-optimal Gated Priority-based Greedy Policies for Two-layer Multi-item Order Fulfillment
Xi Chen, Yuze Chen, Ziyi Chen +1
We study how an e-commerce firm should make real-time fulfillment decisions in a two-layer distribution network when multi-item customer orders arrive sequentially and future deman…
Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability
Yushen Liu, Yin-Jen Chen, Ziyi Chen +4
Many safety-critical control problems are modeled as risk-sensitive partially observable Markov decision processes, where the controller must make decisions from incomplete observa…
From Dual Tracking to Clipping: Provably Faster Distributionally Robust Multi-Objective Optimization
Yufeng Yang, Fangning Zhuo, Ziyi Chen +2
Multi-objective optimization (MOO) has received growing attention in applications that require learning under multiple criteria. However, most existing MOO formulations do not expl…
Provably Efficient Algorithms for S- and Non-Rectangular Robust MDPs with General Parameterization
Anirudh Satheesh, Ziyi Chen, Furong Huang +1
We study robust Markov decision processes (RMDPs) with general policy parameterization under s-rectangular and non-rectangular uncertainty sets. Prior work is largely limited to ta…
Trade-off in Estimating the Number of Byzantine Clients in Federated Learning
Ziyi Chen, Su Zhang, Heng Huang
Federated learning has attracted increasing attention at recent large-scale optimization and machine learning research and applications, but is also vulnerable to Byzantine clients…
Achieve Performatively Optimal Policy for Performative Reinforcement Learning
Ziyi Chen, Heng Huang
Performative reinforcement learning is an emerging dynamical decision making framework, which extends reinforcement learning to the common applications where the agent's policy can…
Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment
Ziyi Chen, Junyi Li, Peiran Yu +1
Reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) are important techniques to align large language models (LLM) with human preference. Howe…
Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality
Shaocong Ma, Ziyi Chen, Yi Zhou +1
The goal of robust constrained reinforcement learning (RL) is to optimize an agent's performance under the worst-case model uncertainty while satisfying safety or resource constrai…
Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
Qi He, Peiran Yu, Ziyi Chen +1
Shuffling-type gradient methods are favored in practice for their simplicity and rapid empirical performance. Despite extensive development of convergence guarantees under various…