Hongyi Tao
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1Optimization and Control×1Stats ML×1
Frequent co-authors
Research Timeline
2026
Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?
This paper explores the convergence of AdamW optimizer under heavy-tailed assumptions in large language models and proposes a corridor lower-bound mechanism.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AImath.OCTheoreticalRecentJun 22, 2026
Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?
Dingzhi Yu, Hongyi Tao, Yuanyu Wan, Luo Luo +1 more
This paper explores the convergence of AdamW optimizer under heavy-tailed assumptions in large language models and proposes a corridor lower-bound mechanism.
View →