Yuchen Zhang



I am a post-doc researcher at Stanford University, hosted by Percy Liang and Moses Charikar. My research explores the frontiers of Artificial Intelligence technology by developing algorithms, building systems and proposing foundamental theory. I am interested in deep learning and non-convex optimization, natural language processing, distributed algorithms, statistical learning theory, crowdsourcing, etc. Prior to Stanford, I got Ph.D. in computer science from UC Berkeley, where I was very fortunate to be advised by Michael Jordan and Martin Wainwright. I got M.A. in statistics from Berkeley, and got B.E. in computer science from Tsinghua University.

As a part-time intern, I have been working with the machine learning group of MSRA on click modeling for web search and online advertising. I also worked with Vanja Josifovski at Google on recommender systems, with Lin Xiao at Microsoft Research on optimization algorithms, and with the web search team of Baidu on burst detection.

Address: Gates 254    Email: zhangyuc (at) cs.stanford.edu    [Google Scholar]
 
 
Manuscripts
 
Splash: User-friendly Programming Interface for Parallelizing Stochastic Algorithms [arXiv] [project website] [GitHub]
Y. Zhang and MI. Jordan
 
Optimality Guarantees for Distributed Statistical Estimation [arXiv]
J. Duchi, MI. Jordan, M. Wainwright, Y. Zhang
 
 
Journal Publications
 
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization [arXiv]
Y. Zhang, L. Xiao
Journal of Machine Learning Research
 
Optimal Prediction for Sparse Linear Models? Lower Bounds for Coordinate-separable M-estimator [pdf]
Y. Zhang, M. Wainwright, MI. Jordan
Electronic Journal of Statistics
 
On Bayes Risk Lower Bounds [pdf]
X. Chen, A. Guntuboyina, Y. Zhang
Journal of Machine Learning Research
 
Spectral Methods meet EM: A Provably Optimal Algorithm for Crowdsourcing [pdf] [GitHub]
Y. Zhang , X. Chen, D. Zhou, MI. Jordan
Journal of Machine Learning Research
 
Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates [pdf]
Y. Zhang , J. Duchi, M. Wainwright
Journal of Machine Learning Research
 
Communication-Efficient Algorithms for Statistical Optimization [pdf]
Y. Zhang , J. Duchi, M. Wainwright
Journal of Machine Learning Research
 
The Antimagicness of the Cartesian Product of Graphs [pdf]
Y. Zhang and X. Sun
Theoretical Computer Science
 
 
Conference Proceedings
 
Inducing Macro Grammars for Efficient Semantic Parsing
Y. Zhang, P. Pasupat, P. Liang
Empirical Methods on Natural Language Processing (EMNLP'17)
 
Convexified Convolutional Neural Networks [pdf] [arXiv] [GitHub] [CodaLab]
Y. Zhang, P. Liang, M. Wainwright
International Conference on Machine Learning (ICML'17)
 
A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics [pdf] [arXiv]
Y. Zhang, P. Liang, M. Charikar
Conference on Learning Theory (COLT'17)    Best Paper Award
 
On the Learnability of Fully-connected Neural Networks [pdf] [arXiv]
Y. Zhang, JD. Lee, M. Wainwright, MI. Jordan
Artificial Intelligence and Statistics (AISTATS'17)
 
Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences [pdf] [arXiv]
C. Jin, Y. Zhang, S. Balakrishnan, M. Wainwright, MI. Jordan
Neural Information Processing System (NIPS'16)
 
L1-regularized Neural Networks are Improperly Learnable in Polynomial Time [pdf] [arXiv]
Y. Zhang, JD. Lee, MI. Jordan
International Conference on Machine Learning (ICML'16)
 
Distributed Estimation of Generalized Matrix Rank: Efficient Algorithms and Lower Bounds [pdf] [arXiv]
Y. Zhang, M. Wainwright, MI. Jordan
International Conference on Machine Learning (ICML'15)
 
DiSCO: Communication-Efficient Distributed Optimization of Self-Concordant Loss [pdf] [arXiv]
Y. Zhang, L. Xiao
International Conference on Machine Learning (ICML'15)
 
Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization [pdf]
Y. Zhang, L. Xiao
International Conference on Machine Learning (ICML'15)
 
Spectral Methods meet EM: A Provably Optimal Algorithm for Crowdsourcing [pdf]
Y. Zhang, X. Chen, D. Zhou, MI. Jordan
Neural Information Processing System (NIPS'14)
 
Lower Bounds on the Performance of Polynomial-time Algorithms for Sparse Linear Regression [pdf] [arXiv]
Y. Zhang, M. Wainwright, MI. Jordan
Conference on Learning Theory (COLT'14)
 
Taxonomy Discovery for Personalized Recommendation [pdf]
Y. Zhang A. Ahmed, V. Josifovski, A. Smola
ACM International Conference on Web Search and Data Mining (WSDM'14)
 
Information-theoretic Lower Bounds for Distributed Statistical Estimation with Communication Constraints [pdf]
Y. Zhang, J. Duchi, MI. Jordan, M. Wainwright
Neural Information Processing System (NIPS'13)
 
Divide and Conquer Kernel Ridge Regression [pdf]
Y. Zhang , J. Duchi, M. Wainwright
Conference on Learning Theory (COLT'13)
 
Communication-Efficient Algorithms for Statistical Optimization [pdf]
Y. Zhang , J. Duchi, M. Wainwright
Neural Information Processing System (NIPS'12)
 
A Noise-aware Click Model for Web Search [pdf]
W. Chen, D. Wang, Y. Zhang, Q. Yang
ACM International Conference on Web Search and Data Mining (WSDM'12)
 
User-click Modeling for Understanding and Predicting Search-behavior [pdf]
Y. Zhang, W. Chen, D. Wang, Q. Yang
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'11)
 
Characterize Search Intent Diversity into Click Models [pdf]
B. Hu, Y. Zhang, W. Chen, G. Wang, Q. Yang
International World Wide Web Conference (WWW'11)
 
Learning Click Model via Probit Bayesian Inference [pdf]
Y. Zhang, D. Wang, G. Wang, W. Chen, Z. Zhang, B. Hu, L. Zhang
ACM Conference on Information and Knowledge Management (CIKM'10)
 
Explore click models for search ranking [pdf]
D. Wang, W. Chen, G. Wang, Y. Zhang, B. Hu
ACM Conference on Information and Knowledge Management (CIKM'10)
 
Incorporating Post-Click Behaviors Into a Click Model [pdf]
F. Zhong, D. Wang, G. Wang, W. Chen, Y. Zhang, Z. Chen, H. Wang
ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'10)
 
Extracting Independent Rules: a New Perspective of Boosting [pdf]
Y. Zhang and L. Zhang
International Symposium on Artificial Intelligence and Mathematics (ISAIM'10)