Xingtu Liu

About

I am a thesis-based Master’s student in computer science at Simon Fraser University, working under the supervision of Prof. Sharan Vaswani. I obtained my Bachelor’s degree in mathematics at University of Waterloo. At UWaterloo, I was fortunate to be advised by Prof. Gautam Kamath. My research interests are broadly in theoretical reinforcement learning and machine learning.

Contact

xingtu_liu at sfu dot ca

Publications & Preprints

Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data.
Gautam Kamath*, Xingtu Liu*, Huanyu Zhang*. (*alphabetical order)
Proceedings of the 39th International Conference on Machine Learning (ICML 2022).
Oral Presentation. (2.1% Acceptance Rate).

Technical Notes

Neural Networks with Complex-Valued Weights Have No Spurious Local Minima.

Teaching

Teaching Assistant
CMPT 120 – Introduction to Computing Science and Programming (Spring 2024)
MACM 101 – Discrete Mathematics (Fall 2023)

Links

CV; Google Scholar; arXiv; Twitter.

Other

My name is pronounced shin-two. My Erdos Number is 4.

“The role of definitions might extend beyond rigor, serving also mathematical creativity itself.“