Pengtao Xie

PhD student, Machine Learning Department,
School of Computer Science, Carnegie Mellon University.
Office: GHC 8229
Email: pengtaoxie2008@gmail.com,  pengtaox@cs.cmu.edu
Social Media: Weibo   Zhihu

Research Interests: latent variable models (LVMs). Specifically, I am interested in (1) designing LVMs to address various complex modeling issues presented in big data; (2) developing geometry regularization approaches of LVMs to capture long-tail knowledge and reduce model complexity; (3) designing distributed systems to facilitate large scale inference and learning of LVMs; (4) developing privacy preservation techniques to protect users' privacy in cloud machine learning. Currently I am focusing on the second and third aspect.

Bio: I am working with Prof. Eric Xing in SAILING lab. My research interests lie in latent variable models, in particular developing geometric regularization approaches to reduce model complexity without compromising expressiveness and building distributed systems to facilitate large scale latent variable modeling.. Before coming to CMU, I obtained a M.E. from Tsinghua University in 2013 and a B.E. from Sichuan University in 2010. I am the recipient of Siebel Scholarship, Goldman Sachs Global Leader Scholarship and National Scholarship of China.

Misc: I am a fan of symphonies and ballet performances. I am also fond of traditional Chinese poems. Occasionally, I write some pseudo poems. In addition, I love traveling. The resolution of the year 2015 is to write a few notes to document my understanding of probabilistic graphical models, which I have been learning, TAing and conducting research on over the past few years.

CV     Research Statement


News

Archived News

Publications


Unpublished Manuscripts


Projects

  • Learning with Diversity: Mutual Angular Regularization of Latent Variable Models [Project Page]
  • Distributed Machine Learning [Project Page]

Teaching

Teaching assistant at Carnegie Mellon University for:

Student Mentoring

  • Yuntian Deng (MS student in Language Technologies Institute, CMU)
  • Yuping Gong (MS student in Language Technologies Institute, CMU)
  • Wanchao Liang (MS student in Information Networking Institute, CMU)
  • Hakim Sidahmed (MS student in Language Technologies Institute, CMU)
  • Yuan Xie (PhD student at Indiana University Bloomington)

Talks

  • Machine Learning Lunch Seminar, Carnegie Mellon University, Sept 2015. Mutual Angular Regularization of Latent Variable Models: Thoery, Algorithm and Applications. [Slides]
  • Beihang University, Aug 2015. Diversifying Restricted Boltzmann Machine for Document Modeling.
  • ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Sydney, Aug 2015. Diversifying Restricted Boltzmann Machine for Document Modeling.
  • VASC Seminar, Carnegie Mellon University, April 2015. Integrating Image Clustering and Codebook Learning.
  • Machine Learning Lunch Seminar, Carnegie Mellon University, April 2015. Integrating Data Clustering and Representation Learning.
  • SCS Student Seminar, Carnegie Mellon University, April 2015. Incorporating Word Correlation Knowledge into Topic Modeling.
  • CL+NLP Seminar, Carnegie Mellon University, Apr 2015. Incorporating Word Correlation Knowledge into Topic Modeling.
  • Database Seminar, Carnegie Mellon University, Mar 2015. Mining User Interests from Personal Photos.
  • 29th AAAI Conference on Artificial Intelligence, Austin, Jan 2015. Integrating Image Clustering and Codebook Learning.
  • Database Seminar, Carnegie Mellon University, Sept 2014. CryptGraph: Privacy Preserving Graph Analytics on Encrypted Graph.
  • Machine Learning Lunch Seminar, Carnegie Mellon University, Sept 2014. Privacy Preserving Neural Network Prediction on Encrypted Data.[Video]
  • Cylab Student Seminar, Carnegie Mellon Unversity, Sep 2014. Privacy-Preserving Neural Network Prediction on Encrypted Data.
  • SDI/ISTC Seminar, Carnegie Mellon Unversity and Intel, Sep 2014. Privacy-Preserving Neural Network Prediction on Encrypted Data.
  • Cloud Machine Learning Team and Machine Learning Group, Microsoft Research, Aug 2014. Privacy-Preserving Neural Network Prediction on Encrypted Data.
  • Cryptography Group, Microsoft Research, Jul 2014. Privacy-Preserving Neural Network Prediction on Encrypted Data.
  • 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013), Beijing, Aug 2013. Multi-Modal Distance Metric Learning.

Professional Activities

  • Program Committee Member for Annual Meeting of the Association for Computational Linguistics (ACL), 2016  
  • Program Committee Member for IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016  
  • Reviewer for Journal of the American Statistical Association (JASA)  
  • Program Committee Member for Annual Meeting of the Association for Computational Linguistics (ACL), 2015  
  • Reviewer for Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015  
  • Reviewer for International Conference on Computer Vision (ICCV), 2015  
  • Reviewer for ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2015  
  • Reviewer for International Conference on Machine Learning (ICML), 2014  
  • Reviewer for IEEE Transactions on Knowledge and Data Engineering (TKDE)  
  • Reviewer for IEEE Transactions on Neural Networks and Learning Systems (TNNLS)  
  • Membership: ACM, IEEE  

Industry Experience

  • Cloud Machine Learning Team and Machine Learning Group, Microsoft Research, Redmond, May 2014 -- Aug 2014.
    Mentors: Thomas Finley, Misha Bilenko, Ran Gilad-Bachrach. I also work closely with Kristin Lauter and Michael Naehrig.
  • Web Search and Mining Group, Microsoft Research Asia, Aug 2009 -- Jun 2010. Mentor: Rong Xiao.

Awards&Honors

  • Siebel Scholarship, 2014. Press Release: [CMU SCS] [CMU] [CMU LTI]
  • KDD Travel Award, 2015
  • CMU Research Fellowship, 2013-2018
  • Excellent Master Graduate Award, Dept. of CS, Tsinghua University, 2013
  • UAI Travel Award, 2013
  • Excellent Bachelor Thesis Award,2010
  • National Scholarship,2009
  • National First Prize in China Undergraduate Mathematical Contest of Modeling (CUMCM),2008
  • Goldman Sachs Global Leader Scholarship,2008