Risultati della ricerca - Lin, F.

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo

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

Testo