Hongyi Zhang （张宏毅）
Starting from May 2019, I will be a Research Scientist in the Applied Machine Learning Group at ByteDance.
I recently graduated from MIT. During my PhD I had a great time working with Prof. Suvrit Sra on a bunch of interesting Riemannian optimization problems. I also joyfully spent two summers at FAIR, mixup and fixup neural networks.
I was also affiliated with LIDS and the Machine Learning Group at MIT.
Innovations today shape our future. My personal take on the most important challenges are: 1) understanding, engineering and enhancing intelligence; 2) affordable, sustainable and high quality pre-college education for all.You can find me at
|2013 - 2019||Massachusetts Institute of Technology|
|Ph.D. in Cognitive Science|
|2008 - 2013||Peking University|
|Bachelor in Machine Intelligence|
|2017/2018 Summer||Research Intern,|
|at Facebook AI Research with Yann Dauphin|
|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|
PublicationsFixup Initialization: Residual Learning Without Normalization. [OpenReview]
7th International Conference on Learning Representations (ICLR 2019).
An Estimate Sequence for Geodesically Convex Optimization. [arXiv]
Proceedings of the 31st Conference On Learning Theory, PMLR 75:1703-1723, 2018.
mixup: Beyond Empirical Risk Minimization. [paper][code]
6th International Conference on Learning Representations (ICLR 2018)
Matrix Completion from O(n) Samples in Linear Time. [Paper][Long version]
Proceedings of the 30th Conference on Learning Theory, PMLR 65:940-947, 2017.
Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds. [Paper]
30th Conference on Neural Information Processing Systems (NIPS 2016)
First-order Methods for Geodesically Convex Optimization. [Paper]
Proceedings of the 29th Conference on Learning Theory, PMLR 49:1617-1638, 2016.
Physics 101: Learning Physical Object Properties from Unlabeled Videos. [Paper][Project]
Proceedings of the British Machine Vision Conference 2016 (BMVC 2016)
Writing Customized Proposals for Probabilistic Programs as Probabilistic Programs.
3rd NIPS Workshop on Probabilistic Programming. 2014.
Understanding High-Level Semantics by Modeling Traffic Patterns. [Paper][Supplemental][Video]
International Conference on Computer Vision (ICCV'13)