Keyulu Xu

Email: keyulu [at] mit (dot) edu

Office: Stata Center, Bldg 32-G478

Mail: 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430

I am a first-year graduate student in the EECS department at MIT and a member of CSAIL and the Machine Learning group.

I studied mathematics and computer science as an undergraduate at University of British Columbia (UBC) in the beautiful city of Vancouver, where I was fortunate to be advised by Nick Harvey. I spent my last undergraduate year as a research intern at National Institute of Informatics (NII) in Tokyo, where I had the pleasure and honor of working with Ken-ichi Kawarabayashi.

My research interests are in machine learning and theoretical computer science. I am currently working on deep learning, non-convex optimization and representation learning.

Aside from computer science, I enjoy artsy and adventurous activities, such as trading, Mahjong (gambling), hunting and people watching. I like to come up with general theory for everything. Currently, I am working on an ambitious project on creating a general framework for finance, politics and sociology.

Recent News


Email me if you have any questions about my papers or code, or if you would like to collaborate with me.

  1. Nicholas J. A. Harvey and Keyulu Xu. "Generating Random Spanning Trees via Fast Matrix Multiplication." Latin American Theoretical Informatics Symposium (LATIN) 2016. [pdf]
  2. Keyulu Xu and Chen Greif. "Large-scale Sparse Saddle-point Systems Solver." [code]


I have lived and worked in some of the most exciting cities in the world -- Vancouver, NYC, Tokyo and Shanghai.


Some recent talks by Keyulu, with video if available.

Generating Random Spanning Trees via Fast Matrix Multiplication, at LATIN 2016, Ensenada, Mexico. [PPTX]