Arvind Mahankali

Publication Activity (10 Years)

Years Active: 2023-2023
Publications (10 Years): 3

Top Topics

Training Process

Top Venues

Publications

Arvind Mahankali, Haochen Zhang, Kefan Dong, Margalit Glasgow, Tengyu Ma
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. NeurIPS (2023)
Arvind Mahankali, Tatsunori B. Hashimoto, Tengyu Ma
One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention. CoRR (2023)
Arvind Mahankali, Jeff Z. HaoChen, Kefan Dong, Margalit Glasgow, Tengyu Ma
Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time. CoRR (2023)