Neural Network Optimization

Better Approximation and Faster Algorithm Using the Proximal Average NeurIPS 2013 Correlations strike back (again): the case of associative memory retrieval NeurIPS 2013 Fast dropout training ICML 2013 Linear Convergence with Condition Number Independent Access of Full Gradients NeurIPS 2013 Maxout Networks ICML 2013 Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n) NeurIPS 2013 On the difficulty of training recurrent neural networks ICML 2013 On the importance of initialization and momentum in deep learning ICML 2013 On the Linear Convergence of the Proximal Gradient Method for Trace Norm Regularization NeurIPS 2013 Phase Retrieval using Alternating Minimization NeurIPS 2013 The Fast Convergence of Incremental PCA NeurIPS 2013 Understanding Dropout NeurIPS 2013 Variance Reduction for Stochastic Gradient Optimization NeurIPS 2013 A Differentially Private Stochastic Gradient Descent Algorithm for Multiparty Classification AISTATS 2012 A quasi-Newton proximal splitting method NeurIPS 2012 A Stochastic Gradient Method with an Exponential Convergence _Rate for Finite Training Sets NeurIPS 2012 A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes NeurIPS 2012 Deep Learning Made Easier by Linear Transformations in Perceptrons AISTATS 2012 Feature Clustering for Accelerating Parallel Coordinate Descent NeurIPS 2012 Large Scale Distributed Deep Networks NeurIPS 2012 Open Problem: Is Averaging Needed for Strongly Convex Stochastic Gradient Descent? COLT 2012 Scalable nonconvex inexact proximal splitting NeurIPS 2012 A Convergence Analysis of Log-Linear Training NeurIPS 2011 Algorithms for Hyper-Parameter Optimization NeurIPS 2011 Better Mini-Batch Algorithms via Accelerated Gradient Methods NeurIPS 2011