Tengyu Ma

 
             Computer Science Department, Princeton University
             Address: 35 Olden Street, Princeton, NJ, 08540, 
             E-mail: firstname at cs dot princeton dot edu
             Office: 416, CS building
 
 
Hi! I am currently a third year graduate student at Princeton University. I am fortunate to be advised by Professor Sanjeev Arora. My research interets include algorithm design, theoretical machine learning, optimization, etc. Before coming to U.S, I studied at Andrew Chi-Chih Yao's CS pilot class at Tsinghua University. 
 
Awards
 
    2014.04     Simons Award for Graduate Students in Theoretical Computer Science
    2010.12     8th Place in Putnam Mathematical Competition (Putnam10)
    2007.07     Silver Medal in 47th International Mathematical Olympiad (IMO07)
 
 
Publications
 
    Decomposing Overcomplete 3rd Order Tensors using Sum-of-Squares Algorithms
    Rong Ge, Tengyu Ma
    manuscript, 2015  
 
    Online Learning of Eigenvectors
    Dan Garber, Elad Hazan, Tengyu Ma
    manuscript, 2015  
 
    Random Walks on Context Spaces: Towards an Explanation of the Mysteries of Semantic Word Embeddings
    Sanjeev Arora, Yuanzhi Li, Yingyu Liang, Tengyu Ma and Andrej Risteski
    manuscript, 2015  
 
    Sanjeev Arora, Rong Ge, Tengyu Ma and Ankur Moitra
    manuscript, 2014  
 
    Ankit Garg, Tengyu Ma and Huy Nguyễn
    NIPS 2014, oral presentation  
 
    Sanjeev Arora, Aditya Bhaskara, Rong Ge and Tengyu Ma
    ICML 2014 
 
    with Sanjeev Arora, Aditya Bhaskara, and Rong Ge
    manuscript, 2014  
 
    Tengyu Ma, Bo Tang and Yajun Wang
    Proceedings of 30th Symposium on Theoretical Aspects of Computer Science(STACS 2013) 
 
    Tengyu Ma, Xiaoming Sun and Huacheng Yu
    Proceedings of 17th International Computing and Combinatorics Conference(COCOON 2011)
 
    Tengyu Ma, Xiaoming Sun and Huacheng Yu
    Designs, Codes, and Cryptography
 
Talks
 
    Analyzing Non-convex Optimization for Dictionary Learning
    MSR Redmond, Nev 2014, Redmond, USA
    Dagstuhl Seminar, Sep 2014, Dagstuhl, Germany
 
    Provable Bounds for Learning Some Deep Representations
    ICML, Jun 2014, Beijing, China
    Columbia theory lunch, Feb 2014, NYC, USA
    CMU theory lunch, Feb 2014, Pittsburgh, USA
 
    The simulate greedy algorithm for several submodular matroid secretary problems
    30th Symposium on Theoretical Aspects of Computer Science(STACS), Kiel, Germany, Feb 2013 [slides]
 
    A new variation of hat guessing games
    17th International Computing and Combinatorics Conference(COCOON), Dallas, Texas, Aug 2011 [slides]