Resume (PDF, HTML)
         
  Xueyuan Zhou

PhD, Computer Science,
University of Chicago
1100 East 58th Street, Chicago, IL 60637

  Research Interests  
  Dissertation online.
Book chapter "Semi-Supervised Learning: Some Recent Advances" in
"Cost-Sensitive Machine Learning"
Convocation: December 9, 2011. 		Statistical machine learning and large scale data mining

  • Practical multivariate nonparametric regression on nonlinear manifolds in high dimensions
  • Manifold learning, semi-supervised learning, dimensionality reduction, kernel methods and AdaBoost
  • Online portfolio selection, and application of machine learning to time series
  • Information retrieval, ranking, text and web mining
    •
     
    Selected Publications
    		 Locations of visitors to this page
  • Xueyuan Zhou, Mikhail Belkin and Nathan Srebro, An Iterated Graph Laplacian Approach for Ranking on Manifolds, In the 17th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2011), 2011, [PDF]. Early version in Snowbird learning workshop.

  • Xueyuan Zhou and Mikhail Belkin, Behavior of Graph Laplacians on Manifolds with Boundary, In arXiv e-print arXiv:1105.3931v1 [cs.LG], May, 2011 [PDF]
    ----- NOTICE: if you know graph Laplacian, but do not know it is a Neumann Laplacian, check this out. This paper also includes several important implications for learning that are not well known.

  • Xueyuan Zhou and Mikhail Belkin, Semi-supervised Learning by Higher Order Regularization, In the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2011), 2011 [PDF]
    ----- NOTICE: if you like the popular quadratic form fLf in semi-supervised learning, check this out. We show it is "ill-posed" except in one-dimensional space, and we also have a nice solution.

    		•
  • Xueyuan Zhou and Nathan Srebro, Error Analysis of Laplacian Eigenmaps for Semi-supervised Learning, In the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2011), 2011 [PDF]
  • Boaz Nadler, Nathan Srebro and Xueyuan Zhou, Semi-Supervised Learning with the Graph Laplacian: The Limit of Infinite Unlabelled Data, In the Twenty-Third Annual Conference on Neural Information Processing Systems (NIPS2009), 2009 [PDF]
    •