9 papers
The Sample Complexity of Multiclass and Sparse Contextual Bandits
Liad Erez, Fan Chen, Alon Cohen +4
We study contextual bandits in the stochastic i.i.d.\ setting, where a learner observes contexts drawn from an unknown distribution, selects actions from a finite set , and aims…
Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression
Fan Chen, Jian Qian, Alexander Rakhlin +1
Self-normalized martingale inequalities lie at the heart of confidence ellipsoids for online least squares and, more broadly, many bandit and reinforcement-learning results. Yet ex…
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
Noah Golowich, Fan Chen, Dhruv Rohatgi +4
Inference-time methods that aggregate and prune multiple samples have emerged as a powerful paradigm for steering large language models, yet we lack any principled understanding of…
MEC Task Offloading in AIoT: A User-Centric DRL Model Splitting Inference Scheme
Weixi Li, Rongzuo Guo, Yuning Wang +1
With the rapid development of the Artificial Intelligence of Things (AIoT), mobile edge computing (MEC) becomes an essential technology underpinning AIoT applications. However, mul…
Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
Yurun Yuan, Fan Chen, Zeyu Jia +2
Policy-based methods currently dominate reinforcement learning (RL) pipelines for large language model (LLM) reasoning, leaving value-based approaches largely unexplored. We revisi…
Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regression
Fan Chen, Jiachun Li, Alexander Rakhlin +1
We study the statistical complexity of private linear regression under an unknown, potentially ill-conditioned covariate distribution. Somewhat surprisingly, under privacy constrai…