Torthaí cuardaigh - Lin, F.

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán

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

Faigh an téacs iomlán