Alert button
Picture for Yan Dai

Yan Dai

Alert button

Refined Sample Complexity for Markov Games with Independent Linear Function Approximation

Feb 11, 2024
Yan Dai, Qiwen Cui, Simon S. Du

Viaarxiv icon

Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise

Feb 02, 2024
Kwangjun Ahn, Zhiyu Zhang, Yunbum Kook, Yan Dai

Viaarxiv icon

The Crucial Role of Normalization in Sharpness-Aware Minimization

May 24, 2023
Yan Dai, Kwangjun Ahn, Suvrit Sra

Figure 1 for The Crucial Role of Normalization in Sharpness-Aware Minimization
Figure 2 for The Crucial Role of Normalization in Sharpness-Aware Minimization
Figure 3 for The Crucial Role of Normalization in Sharpness-Aware Minimization
Figure 4 for The Crucial Role of Normalization in Sharpness-Aware Minimization
Viaarxiv icon

Refined Regret for Adversarial MDPs with Linear Function Approximation

Jan 30, 2023
Yan Dai, Haipeng Luo, Chen-Yu Wei, Julian Zimmert

Figure 1 for Refined Regret for Adversarial MDPs with Linear Function Approximation
Viaarxiv icon

Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning

Jan 25, 2023
Jiatai Huang, Yan Dai, Longbo Huang

Figure 1 for Banker Online Mirror Descent: A Universal Approach for Delayed Online Bandit Learning
Viaarxiv icon

Skeleton-based Action Recognition via Adaptive Cross-Form Learning

Jun 30, 2022
Xuanhan Wang, Yan Dai, Lianli Gao, Jingkuan Song

Figure 1 for Skeleton-based Action Recognition via Adaptive Cross-Form Learning
Figure 2 for Skeleton-based Action Recognition via Adaptive Cross-Form Learning
Figure 3 for Skeleton-based Action Recognition via Adaptive Cross-Form Learning
Figure 4 for Skeleton-based Action Recognition via Adaptive Cross-Form Learning
Viaarxiv icon

Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback

May 26, 2022
Yan Dai, Haipeng Luo, Liyu Chen

Figure 1 for Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback
Viaarxiv icon

Variance-Aware Sparse Linear Bandits

May 26, 2022
Yan Dai, Ruosong Wang, Simon S. Du

Figure 1 for Variance-Aware Sparse Linear Bandits
Viaarxiv icon

Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits

Jan 28, 2022
Jiatai Huang, Yan Dai, Longbo Huang

Figure 1 for Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
Viaarxiv icon

Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays

Oct 26, 2021
Jiatai Huang, Yan Dai, Longbo Huang

Figure 1 for Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays
Viaarxiv icon