Alexander Rakhlin
~Alexander_Rakhlin1
10
论文总数
5.0
年均投稿
平均评分
接收情况9/10
会议分布
NeurIPS
6
ICML
2
ICLR
2
发表论文 (10 篇)
20256 篇
4
Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
ICML 2025Poster
5
GaussMark: A Practical Approach for Structural Watermarking of Language Models
ICML 2025Poster
5
Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
NeurIPS 2025Poster
4
Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
NeurIPS 2025Poster
4
Transformers are Efficient Compilers, Provably
ICLR 2025Rejected
4
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
ICLR 2025Poster
20244 篇
4
The Power of Resets in Online Reinforcement Learning
NeurIPS 2024Spotlight
4
How Does Variance Shape the Regret in Contextual Bandits?
NeurIPS 2024Poster
4
Online Estimation via Offline Estimation: An Information-Theoretic Framework
NeurIPS 2024Poster
4
Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
NeurIPS 2024Spotlight