English
Related papers

Related papers: Oracle-Robust Online Alignment for Large Language …

200 papers

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

This work studies the challenge of aligning large language models (LLMs) with offline preference data. We focus on alignment by Reinforcement Learning from Human Feedback (RLHF) in particular. While popular preference optimization methods…

Machine Learning · Computer Science 2024-06-07 Xiang Ji , Sanjeev Kulkarni , Mengdi Wang , Tengyang Xie

Robust optimization is a common framework in optimization under uncertainty when the problem parameters are not known, but it is rather known that the parameters belong to some given uncertainty set. In the robust optimization framework the…

Optimization and Control · Mathematics 2014-02-27 Aharon Ben-Tal , Elad Hazan , Tomer Koren , Shie Mannor

The classical algorithms for online learning and decision-making have the benefit of achieving the optimal performance guarantees, but suffer from computational complexity limitations when implemented at scale. More recent sophisticated…

Machine Learning · Computer Science 2022-10-19 Guanghui Wang , Zihao Hu , Vidya Muthukumar , Jacob Abernethy

We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the frame of contextual dueling bandits. This formulation,…

Machine Learning · Computer Science 2024-11-12 Zichen Liu , Changyu Chen , Chao Du , Wee Sun Lee , Min Lin

Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, optimizing model outputs to satisfy diverse objectives with…

Computation and Language · Computer Science 2025-03-04 Raghav Gupta , Ryan Sullivan , Yunxuan Li , Samrat Phatale , Abhinav Rastogi

We revisit the question of reducing online learning to approximate optimization of the offline problem. In this setting, we give two algorithms with near-optimal performance in the full information setting: they guarantee optimal regret and…

Machine Learning · Computer Science 2018-04-24 Elad Hazan , Wei Hu , Yuanzhi Li , Zhiyuan Li

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Computation and Language · Computer Science 2025-06-12 Yuxin Jiang

Online matching problems arise in many complex systems, from cloud services and online marketplaces to organ exchange networks, where timely, principled decisions are critical for maintaining high system performance. Traditional heuristics…

Machine Learning · Statistics 2025-10-09 Chiara Mignacco , Matthieu Jonckheere , Gilles Stoltz

Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target metrics, while neglecting rigorous standardized evaluation,…

Machine Learning · Computer Science 2025-02-24 Leo Schwinn , Yan Scholten , Tom Wollschläger , Sophie Xhonneux , Stephen Casper , Stephan Günnemann , Gauthier Gidel

We revisit the problem of \textit{online linear optimization} in case the set of feasible actions is accessible through an approximated linear optimization oracle with a factor $\alpha$ multiplicative approximation guarantee. This setting…

Machine Learning · Computer Science 2017-09-12 Dan Garber

We study offline constrained reinforcement learning from human feedback with multiple preference oracles. Motivated by applications that trade off performance with safety or fairness, we aim to maximize target population utility subject to…

Machine Learning · Computer Science 2026-04-02 Brenden Latham , Mehrdad Moharrami

Direct alignment methods are increasingly used for aligning large language models (LLMs) with human preferences. However, these methods suffer from the issues of verbosity and likelihood displacement, which can be driven by the noisy…

Computation and Language · Computer Science 2025-10-28 Peter Chen , Xi Chen , Wotao Yin , Tianyi Lin

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…

Machine Learning · Computer Science 2025-07-23 Debangshu Banerjee , Kintan Saha , Aditya Gopalan

In this paper, we aim to utilize only offline trajectory data to train a policy for multi-objective RL. We extend the offline policy-regularized method, a widely-adopted approach for single-objective offline RL problems, into the…

Machine Learning · Computer Science 2024-01-05 Qian Lin , Chao Yu , Zongkai Liu , Zifan Wu

Reinforcement Learning from Human Feedback (RLHF) effectively aligns Large Language Models (LLMs) with aggregate human preferences but often fails to address the diverse and conflicting needs of individual users. To overcome this issue, we…

Machine Learning · Computer Science 2026-05-21 Yinlam Chow , Guy Tennenholtz , Ted Yun , James Harrison , Arthur Gretton , Andre Barreto , Bo Dai

This article reviews the recent advances on the statistical foundation of reinforcement learning (RL) in the offline and low-adaptive settings. We will start by arguing why offline RL is the appropriate model for almost any real-life ML…

Machine Learning · Computer Science 2025-01-07 Ming Yin , Mengdi Wang , Yu-Xiang Wang

Prior work in multi-objective reinforcement learning typically uses linear reward scalarization with fixed weights, which provably fails to capture non-convex Pareto fronts and thus yields suboptimal results. This limitation becomes…

Machine Learning · Computer Science 2026-04-01 Yining Lu , Zilong Wang , Shiyang Li , Xin Liu , Changlong Yu , Qingyu Yin , Zhan Shi , Zixuan Zhang , Meng Jiang

Many statistical estimation procedures lead to nonconvex optimization problems. Algorithms to solve these are often guaranteed to output a stationary point of the optimization problem. Oracle inequalities are an important theoretical…

Statistics Theory · Mathematics 2018-02-28 Andreas Elsener , Sara van de Geer

Robust optimization (RO) has emerged as one of the leading paradigms to efficiently model parameter uncertainty. The recent connections between RO and problems in statistics and machine learning domains demand for solving RO problems in…

Optimization and Control · Mathematics 2017-11-21 Nam Ho-Nguyen , Fatma Kilinc-Karzan
‹ Prev 1 2 3 10 Next ›