Hello! I am a second-year PhD student in the ECE department at Princeton University. I am broadly interested in the theoretical foundations of machine learning and large language models. Previously, I graduated from UT Austin's Turing Scholars program with double majors in computer science and mathematics.
Email: stanley.wei [at] princeton.edu
Research
- Provable unlearning in topic modeling and downstream tasks
- Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot
- On the Synergy Between Label Noise and Learning Rate Annealing in Neural Network Training
Stanley Wei, Sadhika Malladi, Sanjeev Arora, Amartya Sanyal
[pdf] Preprint.
Zixuan Wang, Stanley Wei, Daniel Hsu, Jason D. Lee
[pdf] In ICML 2024.
Stanley Wei, Tongzheng Ren, Simon S. Du
[pdf] In NeurIPS 2023 Workshop on Optimization for Machine Learning.
Teaching
- EGR 156: Multivariable Calculus, Princeton University, Fall 2024
- CS 364M: Principles of Machine Learning, UT Austin, Spring 2023
Awards
- Dean's Honored Graduate, UT Austin (2023)
- 26th Place, ICPC World Finals (2022)
- Top 100, Putnam Competition (2020, hosted unofficially due to COVID-19)