Neural Network Optimization

Learning to learn by gradient descent by gradient descent NeurIPS 2016 Linear Convergence of Randomized Feasible Descent Methods Under the Weak Strong Convexity Assumption JMLR 2016 Maximal Sparsity with Deep Networks? NeurIPS 2016 Measuring the Information Content of Financial News COLING 2016 Memory-Efficient Backpropagation Through Time NeurIPS 2016 Model Adaptation and Active Learning in the BBN Speech Activity Detection System for the DARPA RATS Program Interspeech 2016 Model-Based Parametric Prosody Synthesis with Deep Neural Network Interspeech 2016 Multidimensional Residual Learning Based on Recurrent Neural Networks for Acoustic Modeling Interspeech 2016 Natural-Parameter Networks: A Class of Probabilistic Neural Networks NeurIPS 2016 Neural Paraphrase Generation with Stacked Residual LSTM Networks COLING 2016 Noisy Activation Functions ICML 2016 On Lower and Upper Bounds in Smooth and Strongly Convex Optimization JMLR 2016 On the Influence of Momentum Acceleration on Online Learning JMLR 2016 On the Quality of the Initial Basin in Overspecified Neural Networks ICML 2016 Optimal Architectures in a Solvable Model of Deep Networks NeurIPS 2016 Optimal Learning for Multi-pass Stochastic Gradient Methods NeurIPS 2016 Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations NeurIPS 2016 Persistent RNNs: Stashing Recurrent Weights On-Chip ICML 2016 Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences NeurIPS 2016 Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization NeurIPS 2016 Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI Interspeech 2016 Real-Time Tracking of Speakers’ Emotions, States, and Traits on Mobile Platforms Interspeech 2016 Recurrent Orthogonal Networks and Long-Memory Tasks ICML 2016 Refining Architectures of Deep Convolutional Neural Networks CVPR 2016 Residual Networks Behave Like Ensembles of Relatively Shallow Networks NeurIPS 2016