Resultados de búsqueda - Lin, F.

Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline por Huang, Yichen, Yang, Lin F.

Enlace del recurso

Confident Natural Policy Gradient for Local Planning in $q_π$-realizable Constrained MDPs por Tian, Tian, Yang, Lin F., Szepesvári, Csaba

Enlace del recurso

Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model por Liu, Xingtu, Yang, Lin F., Vaswani, Sharan

Enlace del recurso

Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs por Wei, Yukuan, Li, Xudong, Yang, Lin F.

Enlace del recurso

Near-Optimal Sample Complexity for Online Constrained MDPs por Liu, Chang, Li, Yunfan, Yang, Lin F.

Enlace del recurso

Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error por Du, Ally Yalei, Yang, Lin F., Wang, Ruosong

Enlace del recurso

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds por Huang, Jiayi, Zhong, Han, Wang, Liwei, Yang, Lin F.

Enlace del recurso

Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning por Liu, Junyan, Li, Yunfan, Wang, Ruosong, Yang, Lin F.

Enlace del recurso

Learning for Bandits under Action Erasures por Hanna, Osama, Karakas, Merve, Yang, Lin F., Fragouli, Christina

Enlace del recurso

Does Feedback Help in Bandits with Arm Erasures? por Karakas, Merve, Hanna, Osama, Yang, Lin F., Fragouli, Christina

Enlace del recurso

On the optimal regret of collaborative personalized linear bandits por Huang, Bruce, Zhou, Ruida, Yang, Lin F., Diggavi, Suhas

Enlace del recurso

Best-Arm Identification with Noisy Actuation por Karakas, Merve, Hanna, Osama, Yang, Lin F., Fragouli, Christina

Enlace del recurso

Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels por Hanna, Osama A., Karakas, Merve, Yang, Lin F., Fragouli, Christina

Enlace del recurso

Don't Forget to Connect! Improving RAG with Graph-based Reranking por Dong, Jialin, Fatemi, Bahare, Perozzi, Bryan, Yang, Lin F., Tsitsulin, Anton

Enlace del recurso

ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization por Liu, Lawrence, Liu, Alexander, Wang, Mengdi, Zhao, Tuo, Yang, Lin F.

Enlace del recurso

A geometric distortion solution specifically for historical observations and its implementation por Lin, F. R., Peng, Q. Y., Zheng, Z. J., Guo, B. F.

Enlace del recurso

Precision premium transformation -- a high-precision astrometric solution based on the precision premium curve por Zheng, Z. J., Peng, Q. Y., Lin, F. R., Li, D., Zheng, Y.

Enlace del recurso

Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning por Wang, Yiran, Liu, Chenshu, Li, Yunfan, Amani, Sanae, Zhou, Bolei, Yang, Lin F.

Enlace del recurso

NoWag: A Unified Framework for Shape Preserving Compression of Large Language Models por Liu, Lawrence, Chakrabarti, Inesh, Li, Yixiao, Wang, Mengdi, Zhao, Tuo, Yang, Lin F.

Enlace del recurso

LACONIC: Length-Aware Constrained Reinforcement Learning for LLM por Liu, Chang, Zhao, Yiran, Liu, Lawrence, Ye, Yaoqi, Szepesvári, Csaba, Yang, Lin F.

Enlace del recurso