English
Related papers

Related papers: Efficient Federated RLHF via Zeroth-Order Policy O…

200 papers

The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these…

Machine Learning · Computer Science 2024-03-06 Zixuan Liu , Xiaolin Sun , Zizhan Zheng

Single-point zeroth-order optimization (SZO) is useful in solving online black-box optimization and control problems in time-varying environments, as it queries the function value only once at each time step. However, the vanilla SZO method…

Optimization and Control · Mathematics 2022-06-20 Xin Chen , Yujie Tang , Na Li

Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference…

Machine Learning · Computer Science 2024-06-25 Mucong Ding , Souradip Chakraborty , Vibhu Agrawal , Zora Che , Alec Koppel , Mengdi Wang , Amrit Bedi , Furong Huang

Zeroth-order (ZO) optimization with ordinal feedback has emerged as a fundamental problem in modern machine learning systems, particularly in human-in-the-loop settings such as reinforcement learning from human feedback, preference…

Optimization and Control · Mathematics 2025-12-23 Haishan Ye

This work tackles the problem of overoptimization in reinforcement learning from human feedback (RLHF), a prevalent technique for aligning models with human preferences. RLHF relies on reward or preference models trained on \emph{fixed…

Machine Learning · Computer Science 2025-03-11 Dhawal Gupta , Adam Fisch , Christoph Dann , Alekh Agarwal

This paper studies reinforcement learning from human feedback (RLHF) for aligning large language models with human preferences. While RLHF has demonstrated promising results, many algorithms are highly sensitive to misspecifications in the…

Machine Learning · Computer Science 2025-10-30 Erhan Xu , Kai Ye , Hongyi Zhou , Luhan Zhu , Francesco Quinzan , Chengchun Shi

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 constraints. In this paper, we demonstrate that strong duality does…

Machine Learning · Computer Science 2025-09-23 Shaocong Ma , Ziyi Chen , Yi Zhou , Heng Huang

Aligning large language models with human preferences is essential for improving interaction quality and safety by ensuring outputs better reflect human values. A promising strategy involves Reinforcement Learning from Human Feedback…

Information Retrieval · Computer Science 2025-12-17 Jiacong Zhou , Xianyun Wang , Min Zhang , Jun Yu

Fine-tuning large models on edge devices is severely hindered by the memory-intensive backpropagation (BP) in standard frameworks like federated learning and split learning. While substituting BP with zeroth-order optimization can…

Machine Learning · Computer Science 2026-05-28 Qiyuan Chen , Xian Wu , Yi Wang , Xianhao Chen

Offline algorithms for Reinforcement Learning from Human Preferences (RLHF), which use only a fixed dataset of sampled responses given an input, and preference feedback among these responses, have gained increasing prominence in the…

Machine Learning · Computer Science 2025-02-12 Alekh Agarwal , Christoph Dann , Teodor V. Marinov

Federated learning has become a promising distributed learning concept with extra insurance on data privacy. Extensive studies on various models of Federated learning have been done since the coinage of its term. One of the important…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-24 Amir Ali-Pour , Sadra Bekrani , Laya Samizadeh , Julien Gascon-Samson

Federated learning (FL) is a subfield of machine learning where multiple clients try to collaboratively learn a model over a network under communication constraints. We consider finite-sum federated optimization under a second-order…

Machine Learning · Computer Science 2023-05-24 Ahmed Khaled , Chi Jin

When personalized federated learning (FL) meets large foundation models, new challenges arise from various limitations in resources. In addition to typical limitations such as data, computation, and communication costs, access to the models…

Artificial Intelligence · Computer Science 2023-10-10 Wang Lu , Hao Yu , Jindong Wang , Damien Teney , Haohan Wang , Yiqiang Chen , Qiang Yang , Xing Xie , Xiangyang Ji

Reinforcement Learning from Human Feedback (RLHF) is key to aligning Large Language Models (LLMs), typically paired with the Proximal Policy Optimization (PPO) algorithm. While PPO is a powerful method designed for general reinforcement…

Machine Learning · Computer Science 2024-05-17 Ziniu Li , Tian Xu , Yushun Zhang , Zhihang Lin , Yang Yu , Ruoyu Sun , Zhi-Quan Luo

We study a Federated Reinforcement Learning (FedRL) problem with constraint heterogeneity. In our setting, we aim to solve a reinforcement learning problem with multiple constraints while $N$ training agents are located in $N$ different…

Machine Learning · Computer Science 2024-05-07 Hao Jin , Liangyu Zhang , Zhihua Zhang

Fine-tuning large language models (LLMs) on human preferences, typically through reinforcement learning from human feedback (RLHF), has proven successful in enhancing their capabilities. However, ensuring the safety of LLMs during…

Artificial Intelligence · Computer Science 2025-04-09 Wenxuan Zhang , Philip H. S. Torr , Mohamed Elhoseiny , Adel Bibi

Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free.…

Computation and Language · Computer Science 2024-10-11 Shusheng Xu , Wei Fu , Jiaxuan Gao , Wenjie Ye , Weilin Liu , Zhiyu Mei , Guangju Wang , Chao Yu , Yi Wu

Large Language Models (LLMs) can acquire extensive world knowledge through pre-training on large corpora. However, due to exposure to low-quality data, LLMs may exhibit harmful behavior without aligning with human values. The dominant…

Machine Learning · Computer Science 2023-10-11 Tianhao Wu , Banghua Zhu , Ruoyu Zhang , Zhaojin Wen , Kannan Ramchandran , Jiantao Jiao

Safe derivative-free optimization under unknown constraints is a fundamental challenge in modern learning and control. Existing zeroth-order (ZO) methods typically still assume access to a first-order oracle of the constraint functions or…

Optimization and Control · Mathematics 2026-01-29 Runyu Zhang , Gioele Zardini , Asuman Ozdaglar , Jeff Shamma , Na Li

Aligning large language models (LLMs) with human preferences in federated learning (FL) is challenging due to decentralized, privacy-sensitive, and highly non-IID preference data. Direct Preference Optimization (DPO) offers an efficient…

Machine Learning · Computer Science 2026-03-23 Kewen Zhu , Liping Yi , Zhiming Zhao , Zhuang Qi , Han Yu , Qinghua Hu