Neural Network Optimization

Accelerating Natural Gradient with Higher-Order Invariance ICML 2018 Action-dependent Control Variates for Policy Optimization via Stein Identity ICLR 2018 Adafactor: Adaptive Learning Rates with Sublinear Memory Cost ICML 2018 Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems AISTATS 2018 Adaptive Methods for Nonconvex Optimization NeurIPS 2018 Adaptive Weighting for Neural Machine Translation COLING 2018 Adding One Neuron Can Eliminate All Bad Local Minima NeurIPS 2018 A Full End-to-End Semantic Role Labeler, Syntactic-agnostic Over Syntactic-aware? COLING 2018 A Generic Approach for Escaping Saddle points AISTATS 2018 Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced NeurIPS 2018 Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations COLT 2018 Analysing the Focus of a Hierarchical Attention Network: the Importance of Enjambments When Classifying Post-modern Poetry Interspeech 2018 An Encoder-Decoder Approach to the Paradigm Cell Filling Problem EMNLP 2018 An intriguing failing of convolutional neural networks and the CoordConv solution NeurIPS 2018 A PID Controller Approach for Stochastic Optimization of Deep Networks CVPR 2018 Approximating Real-Time Recurrent Learning with Random Kronecker Factors NeurIPS 2018 A Priori SNR Estimation Based on a Recurrent Neural Network for Robust Speech Enhancement Interspeech 2018 A Progressive Batching L-BFGS Method for Machine Learning ICML 2018 Audiovisual Speech Activity Detection with Advanced Long Short-Term Memory Interspeech 2018 A Unified Analysis of Stochastic Momentum Methods for Deep Learning IJCAI 2018 Automatic Differentiation in Machine Learning: a Survey JMLR 2018 Automatic differentiation in ML: Where we are and where we should be going NeurIPS 2018 Automatic DNN Node Pruning Using Mixture Distribution-based Group Regularization Interspeech 2018 Backpropagating through Structured Argmax using a SPIGOT ACL 2018 Backpropagation through the Void: Optimizing control variates for black-box gradient estimation ICLR 2018