2 citations · 5 across the 13 of their papers we have counts for
13 papers
When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection
Zhengyu Hu, Zheyuan Xiao, Linxin Song +10
LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current practice often chooses the high…
On the Complexity of Best-Arm Identification in Non-Stationary Linear Bandits
Leo Maynard-Zhang, Zhihan Xiong, Kevin Jamieson +1
We study the fixed-budget best-arm identification (BAI) problem in non-stationary linear bandits. Concretely, given a fixed time budget , finite arm set $\mathcal{…
LoRe: Personalizing LLMs via Low-Rank Reward Modeling
Avinandan Bose, Zhihan Xiong, Yuejie Chi +3
Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning fr…
Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration
Avinandan Bose, Zhihan Xiong, Aadirupa Saha +2
Reinforcement Learning from Human Feedback (RLHF) is currently the leading approach for aligning large language models with human preferences. Typically, these models rely on exten…
Dual Approximation Policy Optimization
Zhihan Xiong, Maryam Fazel, Lin Xiao
We propose Dual Approximation Policy Optimization (DAPO), a framework that incorporates general function approximation into policy mirror descent methods. In contrast to the popula…
Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators
Zhengyu Hu, Jieyu Zhang, Zhihan Xiong +3
Despite the remarkable success of Large Language Models (LLMs), evaluating their outputs' quality regarding preference remains a critical challenge. While existing works usually le…
A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity
Zhihan Xiong, Romain Camilleri, Maryam Fazel +2
We investigate the fixed-budget best-arm identification (BAI) problem for linear bandits in a potentially non-stationary environment. Given a finite arm set $\mathcal{X}\subset\mat…
A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
Haozhe Jiang, Qiwen Cui, Zhihan Xiong +2
We investigate learning the equilibria in non-stationary multi-agent systems and address the challenges that differentiate multi-agent learning from single-agent learning. Specific…
Offline congestion games: How feedback type affects data coverage requirement
Haozhe Jiang, Qiwen Cui, Zhihan Xiong +2
This paper investigates when one can efficiently recover an approximate Nash Equilibrium (NE) in offline congestion games. The existing dataset coverage assumption in offline gener…
Learning in Congestion Games with Bandit Feedback
Qiwen Cui, Zhihan Xiong, Maryam Fazel +1
In this paper, we investigate Nash-regret minimization in congestion games, a class of games with benign theoretical structure and broad real-world applications. We first propose a…
Selective Sampling for Online Best-arm Identification
Romain Camilleri, Zhihan Xiong, Maryam Fazel +2
This work considers the problem of selective-sampling for best-arm identification. Given a set of potential options , a learner aims to compute with…
Near-Optimal Randomized Exploration for Tabular Markov Decision Processes
Zhihan Xiong, Ruoqi Shen, Qiwen Cui +2
We study algorithms using randomized value functions for exploration in reinforcement learning. This type of algorithms enjoys appealing empirical performance. We show that when we…
Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning
Tian Tan, Zhihan Xiong, Vikranth R. Dwaracherla
It is well known that quantifying uncertainty in the action-value estimates is crucial for efficient exploration in reinforcement learning. Ensemble sampling offers a relatively co…