Optimization & Theory

How transferable are features in deep neural networks? NeurIPS 2014 Identifying and attacking the saddle point problem in high-dimensional non-convex optimization NeurIPS 2014 Immediate, Scalable Object Category Detection CVPR 2014 Large-Margin Convex Polytope Machine NeurIPS 2014 large scale canonical correlation analysis with iterative least squares NeurIPS 2014 Logistic Regression: Tight Bounds for Stochastic and Online Optimization COLT 2014 Online Optimization for Max-Norm Regularization NeurIPS 2014 On Model Parallelization and Scheduling Strategies for Distributed Machine Learning NeurIPS 2014 On the Computational Efficiency of Training Neural Networks NeurIPS 2014 On the Number of Linear Regions of Deep Neural Networks NeurIPS 2014 Orbit Regularization NeurIPS 2014 Parallel Double Greedy Submodular Maximization NeurIPS 2014 Proximal Quasi-Newton for Computationally Intensive L1-regularized M-estimators NeurIPS 2014 Recovering Surface Details under General Unknown Illumination Using Shading and Coarse Multi-view Stereo CVPR 2014 SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives NeurIPS 2014 Scalable Kernel Methods via Doubly Stochastic Gradients NeurIPS 2014 Self-Paced Learning with Diversity NeurIPS 2014 Signal recovery from Pooling Representations ICML 2014 Spectral k-Support Norm Regularization NeurIPS 2014 Speeding Up Tracking by Ignoring Features CVPR 2014 Stochastic Proximal Gradient Descent with Acceleration Techniques NeurIPS 2014 The limits of squared Euclidean distance regularization NeurIPS 2014 Time--Data Tradeoffs by Aggressive Smoothing NeurIPS 2014 Accelerated Mini-Batch Stochastic Dual Coordinate Ascent NeurIPS 2013 Accelerating Stochastic Gradient Descent using Predictive Variance Reduction NeurIPS 2013