Xuechen Li

University of Toronto

Biography

I am currently a brain resident at Google.

I graduated from the University of Toronto with a specialist in computer science and minors in mathematics and statistics. Broadly speaking, I am interested in almost all aspects of computational statistics and numerical optimization. In particular, I am most experienced with various aspects of Monte Carlo methods in machine learning, both applied and theoretical. I am also familar with niche topics such as numerical methods for ODEs, SDEs, and PDEs. Recently, I am also interested in computational neural science.

During undergrad, I had the great fortune to work on research projects with profs. David Duvenaud, Murat Erdogdu, and Roger Grosse.

In a past life, I used to spend my free time working on traditional CS theory problems such as (discrete) algorithm design and analysis.

Interests

Statistics
Optimization
Machine Learning

Education

BSc in Computer Science, 2019

University of Toronto

Research

Xuechen Li, Denny Wu, Lester Mackey, Murat A. Erdogdu. Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond. Advances in Neural Information Processing Systems (NeurIPS), 2019.

Preprint

George Barmpalias, Neng Huang, Andrew Lewis-Pye, Angsheng Li, Xuechen Li, Yicheng Pan, Tim Roughgarden. The idemetric property: when most distances are (almost) the same. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2019.

PDF

Ricky T. Q. Chen, Xuechen Li, Roger Grosse, David Duvenaud. Isolating Sources of Disentanglement in Variational Autoencoders. Advances in Neural Information Processing Systems (NeurIPS), 2018.

Preprint

Chris Cremer, Xuechen Li, David Duvenaud. Inference Suboptimality in Variational Autoencoders. International Conference on Machine Learning (ICML), 2018.

Preprint

Contact

lxuechen@cs.toronto.edu