Han Zhao     (赵晗)


PhD student
Machine Learning Department
School of Computer Science
Carnegie Mellon University
Email: han (DOT) zhao [AT] cs (DOT) cmu (DOT) edu
Office: GHC 8229
[Curriculum Vitae]

Bio

I am a second year PhD student at the Machine Learning Department, Carnegie Mellon University. I am fortunate to work with my advisor, Prof. Geoff Gordon. Before coming to CMU, I obtained my BEng degree from Department of Computer Science and Technology at Tsinghua University and MMath from the University of Waterloo. My research interests include machine learning and optimization, with particular interests in sequential decision making and inference in probabilistic graphical models.

Education

Machine Learning Department, Carnegie Mellon University
Sep. 2015 -- Present
PhD student
Advisor: Prof. Geoff Gordon
David R. Cheriton School of Computer Science, University of Waterloo
Sep. 2013 -- May. 2015
Master of Mathematics, Computer Science
Advisor: Prof. Pascal Poupart
Department of Computer Science and Technology, Tsinghua University
Aug. 2009 -- Jul. 2013
Bachelor of Engineering, Computer Science
David R. Cheriton School of Computer Science, University of Waterloo
Sep. 2012 -- May. 2013
Non-degree Exchange program
Advisor: Prof. Pascal Poupart

Publications

A Unified Approach for Learning the Parameters of Sum-Product Networks
H. Zhao, P. Poupart and G. Gordon
In Proceedings of the 29th Advances in Neural Information Processing Systems (NIPS 2016)
[abs] [pdf] [supplement] [poster] [code]
Online Algorithms for Sum-Product Networks with Continuous Variables
P. Jaini, A. Rashwan, H. Zhao, Y. Liu, E. Banijamali, Z. Chen and P. Poupart
In Proceedings of the 8th International Conference on Probabilistic Graphical Models (PGM 2016)
[abs] [pdf]
Collapsed Variational Inference for Sum-Product Networks
H. Zhao, T. Adel, G. Gordon and B. Amos
In Proceedings of the 33rd International Conference on Machine Learning (ICML 2016)
[abs] [pdf] [poster] [slides] [code]
Online and Distributed Bayesian Moment Matching for Parameter Learning in Sum-Product Networks
A. Rashwan, H. Zhao and P. Poupart
In Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016)
[abs] [pdf]
On the Relationship between Sum-Product Networks and Bayesian Networks
H. Zhao, M. Melibari and P. Poupart
In Proceedings of the 32nd International Conference on Machine Learning (ICML 2015)
[abs] [pdf] [supplement] [Full arXiv version] [slides] [poster]
Self-Adaptive Hierarchical Sentence Model
H. Zhao, Z. Lu and P. Poupart
In Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI 2015)
[abs] [pdf] [slides] [poster] [code]
SoF: Soft-Cluster Matrix Factorization for Probabilistic Clustering
H. Zhao, P. Pouart, Y. Zhang and M. Lysy
In Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI 2015)
[abs] [pdf] [poster]
Global Network Alignment in the Context Of Aging
F. Faisal, H. Zhao and T. Milenkovic
IEEE/ACM Transactions on Computational Biology and Bioinformatics (IEEE/ACM TCBB 2014)
(an extended journal version of our ACM BCB 2013 paper)
[abs] [pdf] [supplement]
A Sober Look at Spectral Learning
H. Zhao and P. Poupart
In Method of Moments and Spectral Learning workshop at 31th International Conference on Machine Learning (ICML 2014 workshop)
[abs] [pdf] [slides] [poster] [code]
Global Network Alignment in the Context of Aging
T. Milenkovic, H. Zhao and F. Faisal
In Proceedings of the 4th ACM International Conference on Bioinformatics, Computational Biology and Biomedicine (ACM BCB 2013)
[abs] [pdf]

Misc

I enjoy sketching and calligraphy at my spare time. If I have a long vacation, I also enjoy traveling.
I enjoy online learning (not the Online Learning in machine learning) and discussing with people from all over the world. Take a look of Coursera and Edx if you are also interested.