Hongyi Zhang

I am a fourth-year Ph.D. student in the Department of Brain and Cognitive Sciences at MIT working with Dr. Suvrit Sra.

I am also affiliated with LIDS and the Machine Learning Group at MIT.

I aim to combine the power of nonlinear optimization and differential geometry to solve difficult optimization problems. I am interested in machine learning and, more broadly, modeling and solving real world computational problems.

Address: 32D-572
77 Massachusetts Avenue,
Cambridge MA, 02139
Email: hongyiz (at) mit (dot) edu


2013 - Present Massachusetts Institute of Technology
Ph.D. candidate in Cognitive Science
2008 - 2013 Peking University
Bachelor in Machine Intelligence


2015/2016 Fall Teaching Assistant,
MIT 9.520/6.860 -- Statistical Learning Theory and Applications
2014 Fall Teaching Assistant,
MIT 9.66/6.804/9.660 -- Computational Cognitive Science
2012 Summer Research Intern,
at TTI Chicago with Prof. Raquel Urtasun


Matrix Completion from O(n) Samples in Linear Time. [arXiv]
David Gamarnik, Quan Li, Hongyi Zhang. (alphabetic order)
arXiv:1702.02267 [stat.ML] (Short version to appear in COLT 2017)

Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds. [Paper][Supplemental]
Hongyi Zhang, Sashank J. Reddi, Suvrit Sra.
The 30th Conference on Neural Information Processing Systems (NIPS 2016).

First-order Methods for Geodesically Convex Optimization. [Paper]
Hongyi Zhang, Suvrit Sra.
The 29th Annual Conference on Learning Theory (COLT 2016)

Physics 101: Learning Physical Object Properties from Unlabeled Videos. [Paper][Project]
Jiajun Wu, Joseph Lim, Hongyi Zhang, Joshua Tenenbaum and William Freeman.
Proceedings of the British Machine Vision Conference 2016 (BMVC 2016)

Writing Customized Proposals for Probabilistic Programs as Probabilistic Programs.
Hongyi Zhang, Vikash Mansinghka.
3rd NIPS Workshop on Probabilistic Programming. 2014.

Understanding High-Level Semantics by Modeling Traffic Patterns. [Paper][Supplemental][Video]
Hongyi Zhang, Andreas Geiger, Raquel Urtasun.
International Conference on Computer Vision (ICCV'13)