Publications

  • I.J. Goodfellow, Q.V. Le, A.M. Saxe, H. Lee, A.Y. Ng,
    Measuring invariances in deep networks NIPS, 2009. [PDF]
    Topics: invariances, unsupervised learning, neural networks.

  • A. Coates, P. Baumstarck, Q. Le, and A. Y. Ng
    Scalable Learning for Object Detection with GPU Hardware. IROS, 2009. [PDF]
    Topics: object detection, special hardware, GPUs.

  • Q.V. Le, A.Y. Ng.
    Joint calibration of multiple sensors. IROS, 2009. [PDF]
    Topics: robotic sensor calibration.

  • C.H. Teo, S.V.N. Vishwanathan, A. Smola, Q.V. Le.
    Bundle Methods for Regularized Risk Minimization. JMLR (To appear), 2009. [PDF] [Code]
    Topics: learning and large-scale optimization.
    Notes: previous shorter versions appeared in KDD and NIPS with Appendix

  • N. Quadrianto, A.J. Smola, T.S. Caetano, Q.V. Le
    Estimating Labels from Label Proportions. JMLR (To appear), 2009. [PDF]
    Topics: Gaussian Process classification, transduction, semi-supervised learning, prior knowledge.
    Notes: a previous shorter version appeared in ICML

  • M. Quigley, S. Batra, S. Gould, E. Klingbeil, Q.V. Le, A. Wellman, A.Y. Ng.
    High Accuracy 3D Sensing for Mobile Manipulation: Improving Object Detection and Door Opening. ICRA, 2009. [PDF]
    Topics: 3D sensing hardware, object detection, manipulation.

  • C.B. Do, Q.V. Le, C.S. Foo.
    Proximal regularization for online and batch learning. ICML, 2009. [PDF (conference version)] [PDF (extended version, with proofs)]
    Topics: learning and optimization.

  • T.S. Caetano, J.J. McAuley, L. Cheng, Q.V. Le, A.J. Smola.
    Learning Graph Matching. PAMI, 2009. [PDF], [Digital library link], [Code]
    Topics: graph matching, structured estimation.

  • C.B. Do, Q.V. Le, C.H. Teo, O. Chapelle, A.J. Smola.
    Tighter Bounds for Structured Estimation. NIPS 21, 2009. [PDF]
    Topics: structured estimation, computational biology, ranking.

  • N. Quadrianto, A. J. Smola, T. S. Caetano, Q. V. Le.
    Estimating Labels from Label Proportions. ICML, 2008. [PDF]
    Topics: Gaussian Process classification, transduction, semi-supervised learning, prior knowledge.

  • M. Weimer, A. Karatzoglou, Q.V. Le, A.J. Smola.
    COFI RANK - Maximum Margin Matrix Factorization for Collaborative Ranking. NIPS 20, 2008. [PDF] [Code/Website]
    Topics: ranking, collaborative-filtering, structured outputs, optimization.

  • A.J. Smola, S.V.N. Vishwanathan, Q.V. Le.
    Bundle methods for machine learning. NIPS 20, 2008. [PDF] [Appendix], [NIPS spotlight], [Code]
    Topics: optimization, theory.

  • O. Chapelle, Q.V. Le, A.J. Smola.
    Large margin optimization of ranking measures. NIPS Workshop: Machine Learning for Web Search, 2007. [PDF]
    Topics: ranking, structured outputs.

  • Q.V. Le, A.J. Smola.
    Direct optimization or ranking measures. NICTA Tech report, 2007. [PDF]
    Topics: ranking, structured outputs.

  • T. Caetano, L. Cheng, Q.V. Le, A.J. Smola.
    Learning graph matching. ICCV, 2007. [PDF], [Oral presentation], [Code]
    Topics: graph matching, max-margin structured outputs, vision.

  • C.H. Teo, Q.V. Le, A.J. Smola, SVN Vishwanathan.
    A Scalable Modular Convex Solver for Regularized Risk Minimization. KDD, 2007. [PDF], [Code]
    Topics: large-scale optimization, open-source software.

  • Q. V. Le, A. J. Smola, T. Gärtner, Y. Altun.
    Transductive Gaussian Process Regression with Automatic Model Selection. ECML, 2006. Best paper award, [PDF]
    Topics: Gaussian Process regression, transduction.

  • C. Burges, R. Ragno, Q. V. Le.
    Learning to Rank with nonsmooth cost functions. NIPS 19, 2007. [PDF]
    Topics: ranking, neural networks.

  • Q. V. Le, A. J. Smola, T. Gärtner.
    Simpler knowledge-based Support Vector Machines. ICML, 2006. [PDF]
    Topics: prior knowledge, non-convex optimization.

  • T. Gärtner, Q. V. Le, S. Burton, A. J. Smola, S. V. N. Vishwanathan.
    Large-Scale Multiclass Transduction. NIPS 18, 2006. [PDF]
    Topics: Gaussian Process classification, multiclass, transduction.

  • Q. V. Le, A. J. Smola, S. Canu.
    Heteroscedastic Gaussian Process Regression. ICML, 2005. [PDF]
    Topics: Gaussian Process regression.

  • I. Takeuchi, Q. V. Le, T. Sears, A. J. Smola.
    Nonparametric quantile estimation. JMLR 7, 2006. [old PDF], [PDF], [Code(ELEFANT)]
    Topics: quantile estimation, median estimation, theory.

  • Q. V. Le, T. Sears, A. J. Smola.
    Nonparametric quantile estimation. NICTA Technical report, 2005. [PDF]
    Topics: quantile estimation, median estimation, theory.

  • T. Gärtner, T. Horvath, Q. V. Le, A. J. Smola, S. Wrobel.
    Kernel Methods for Graphs. Mining Graph Data (Book chapter). L. Holder, D. Cook (editors), 2005.
    Topics: Gaussian Process classification, graphs.

  • T. Gärtner, Q. V. Le, A. J. Smola.
    A Short Tour of Kernel Methods for Graphs. Tech report. 2006. [PDF]
    Topics: Gaussian Process classification, graphs.

    Demonstrations
  • M. Quigley, S. Batra, S. Gould, E. Klingbeil, Q.V. Le, A. Y. Ng.
    High-Accuracy 3D Sensing for Mobile Manipulators. NIPS 21, 2009. [Videos], [Poster]