I am Shuo Xie (解说), a third-year Ph.D. student at Toyota Technological Institute at Chicago, advised by Professor Zhiyuan Li.
I am currently interested in optimization and LLMs.
Previously, I received a B.S. degree in statistics from Peking University and a M.S. degree in statistics from University of Chicago and did research in natural language processing with Hongyuan Mei and Hao Tan.
[Email][Google Scholar][Github]
A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent
Shuo Xie*, Tianhao Wang*, Beining Wu, Zhiyuan Li
In submission
Provable Benefit of Sign Descent: A Minimal Model Under Heavy-Tailed Class Imbalance
Robin Yadav, Shuo Xie, Tianhao Wang, Zhiyuan Li
NeurIPS 2025 Workshop on Optimization for Machine Learning (Oral)
Should Decision-Makers Reveal the Classifiers in Online Strategic Classification?
($\alpha$-$\beta$) Han Shao, Shuo Xie, Kunhe Yang
ICML 2025
Structured Preconditioners in Adaptive Optimization: A Unified Analysis
Shuo Xie, Tianhao Wang, Sashank reddi, Sanjiv Kumar, Zhiyuan Li
ICML 2025
Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity.
Shuo Xie, Mohamad Amin Mohamadi, Zhiyuan Li
ICLR 2025 (Spotlight)
Implicit Bias of AdamW: $\ell_\infty$-Norm Constrained Optimization
Shuo Xie, Zhiyuan Li
ICML 2024
Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning
Shuo Xie, Jiahao Qiu, Ankita Pasad, Li Du, Qing Qu, Hongyuan Mei
Findings of EMNLP 2022
Gold Medal in Chinese Mathematical Olympiad (CMO)
Rank 1st in Chinese Girls’ Mathematical Olympiad (CGMO)
Outside of research, I enjoy cooking, learning Japanese on Duolingo, playing squash and bouldering.
During my undergraduate time, I was a member of the Peking University Softball Team and the captain of the Softball Team of School of Mathematical Sciences.