Srebro, Nathan - Toyota Technological Institute at Chicago

• Mach Learn (2008) 72: 89112 DOI 10.1007/s10994-008-5059-5
• Fast Maximum Margin Matrix Factorization for Collaborative Prediction
• Learning with Matrix Factorizations
• Linear Dependent Dimensionality Reduction Nathan Srebro Tommi Jaakkola
• TRADING ACCURACY FOR SPARSITY IN OPTIMIZATION PROBLEMS WITH SPARSITY CONSTRAINTS
• Are there local maxima in the infinite-sample likelihood of Gaussian mixture estimation?
• Stochastic Convex Optimization Shai Shalev-Shwartz
• Artificial Intelligence 143 (2003) 123138 www.elsevier.com/locate/artint
• When is Clustering Hard? Nathan Srebro
• Improved Prediction of HIV Resistance In-Vitro by Biochemically-Driven Models
• Fit low-rank (factorizable) matrix X=UV' to observed entries. minimize loss( Xij ; Yij )
• Maximum Likelihood Bounded Tree-Width Markov Networks Nathan Srebro, Massachusetts Institute of Technology (nati@mit.edu)
• Improved Guarantees for Learning via Similarity Functions Maria-Florina Balcan Avrim Blum
• arXiv:1002.2780v1[cs.LG]14Feb2010 Collaborative Filtering in a Non-Uniform World
• Stochastic Optimization for Machine Learning
• Similarity-Based Theoretical Foundation for Sparse Parzen
• Department of Computer Science 6 King's College Rd, Toronto University of Toronto M5S 3G4, Canada
• Adaptive Gaussian Kernel SVMs Nathan Srebro and Sam Roweis
• Maximum Likelihood Bounded Tree-Width Markov Networks Nathan Srebro
• Error Analysis of Laplacian Eigenmaps for Semi-supervised Learning Xueyuan Zhou Nathan Srebro
• Practical Large-Scale Optimization for Max-Norm Regularization
• Tight Sample Complexity of Large-Margin Learning Sivan Sabato1
• Journal of Machine Learning Research 11 (2010) 2635-2670 Submitted 4/10; Revised 9/10; Published 10/10 Learnability, Stability and Uniform Convergence
• Reducing Label Complexity by Learning From Bags Sivan Sabato Nathan Srebro Naftali Tishby
• Learnability and Stability in the General Learning Setting Shai Shalev-Shwartz
• Fast Rates for Regularized Objectives Karthik Sridharan, Nathan Srebro, Shai Shalev-Shwartz
• Iterative Loss Minimization with 1-Norm Constraint and Guarantees on Sparsity
• Low 1-Norm and Guarantees on Sparsifiability Shai Shalev-Shwartz and Nathan Srebro
• Uncovering Shared Structures in Multiclass Classification Yonatan Amit MITMIT@CS.HUJI.AC.IL
• Mathematical Programming manuscript No. (will be inserted by the editor)
• How Good is a Kernel When Used as a Similarity Measure?
• Loss Functions for Preference Levels: Regression with Discrete Ordered Labels
• Rank, Trace-Norm and Max-Norm Nathan Srebro1
• Maximum Margin Matrix Factorization Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology
• How Much Of A Hypertree Can Be Captured By Windmills? Percy Liang Nathan Srebro
• A Dynamic Data Structure for Checking Hyperacyclicity Percy Liang Nathan Srebro
• Sparse Matrix Factorization for Analyzing Gene Expression Patterns
• SVM Optimization: Inverse Dependence on Training Set Size Shai Shalev-Shwartz SHAI@TTI-C.ORG
• 1 Regularization in Infinite Dimensional Feature Spaces Saharon Rosset1
• Maximum-Margin Matrix Factorization Nathan Srebro
• Pegasos: Primal Estimated sub-GrAdient SOlver for SVM Shai Shalev-Shwartz SHAIS@CS.HUJI.AC.IL
• Maximum Likelihood Markov Networks: An Algorithmic Nathan Srebro
• Collaborative Filtering in a Non-Uniform World: Learning with the Weighted Trace Norm
• Similarity-Based Theoretical Foundation for Sparse Parzen Window Maria-Florina Balcan ninamf@cs.cmu.edu
• Low 1-Norm and Guarantees on Sparsifiability Shai Shalev-Shwartz shai@tti-c.org
• Nathan Srebro Tommi Jaakkola Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology
• On the Interaction between Norm and Dimensionality: Multiple Regimes in Learning
• An Iterated Graph Laplacian Approach for Ranking on Manifolds
• Semi-supervised Learning with Density Based Distances Avleen S. Bijral
• A GPU-Tailored Approach for Training Kernelized SVMs Andrew Cotter Nathan Srebro Joseph Keshet
• Beating SGD: Learning SVMs in Sublinear Time Elad Hazan Tomer Koren