Toward Understanding Why Adam Converges Faster Than SGD for Transformers Yan Pan, Yuanzhi Li OPT 2022: Optimization for Machine Learning (NeurIPS 2022 Workshop) [ArXiv][Code][Poster]
Research Projects
Zeroth-Order Online Convex Optimization CMU 10-422 Spring 2023 [Report][Slides]
Conditioning Language Models for Image Paragraph Captioning CMU Summer Undergraduate Research Fellowship (SURF) 2021 [Poster]