Optimization & Theory

Hogwild!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent NeurIPS 2011 Large-Scale Category Structure Aware Image Categorization NeurIPS 2011 Phase transition in the family of p-resistances NeurIPS 2011 Regularized Laplacian Estimation and Fast Eigenvector Approximation NeurIPS 2011 Shallow vs. Deep Sum-Product Networks NeurIPS 2011 A Dirty Model for Multi-task Learning NeurIPS 2010 A Family of Penalty Functions for Structured Sparsity NeurIPS 2010 An analysis on negative curvature induced by singularity in multi-layer neural-network learning NeurIPS 2010 Deterministic Single-Pass Algorithm for LDA NeurIPS 2010 LSTD with Random Projections NeurIPS 2010 On the Convergence Properties of Contrastive Divergence AISTATS 2010 Parallelized Stochastic Gradient Descent NeurIPS 2010 REGO: Rank-based Estimation of Renyi Information using Euclidean Graph Optimization AISTATS 2010 Regularized estimation of image statistics by Score Matching NeurIPS 2010 Relaxed Clipping: A Global Training Method for Robust Regression and Classification NeurIPS 2010 Smoothness, Low Noise and Fast Rates NeurIPS 2010 Space-Variant Single-Image Blind Deconvolution for Removing Camera Shake NeurIPS 2010 Spatial and anatomical regularization of SVM for brain image analysis NeurIPS 2010 Spectral Regularization for Support Estimation NeurIPS 2010 Tight Sample Complexity of Large-Margin Learning NeurIPS 2010 Understanding the difficulty of training deep feedforward neural networks AISTATS 2010 Fast Image Deconvolution using Hyper-Laplacian Priors NeurIPS 2009 Heavy-Tailed Symmetric Stochastic Neighbor Embedding NeurIPS 2009 Kernel Methods for Deep Learning NeurIPS 2009 Measuring Invariances in Deep Networks NeurIPS 2009