Neural Network Optimization

Improving Training of Deep Neural Networks via Singular Value Bounding CVPR 2017 Joint Training of Expanded End-to-End DNN for Text-Dependent Speaker Verification Interspeech 2017 Learned Optimizers that Scale and Generalize ICML 2017 Learning Gradient Descent: Better Generalization and Longer Horizons ICML 2017 Learning ReLUs via Gradient Descent NeurIPS 2017 Learning to Learn without Gradient Descent by Gradient Descent ICML 2017 Less than a Single Pass: Stochastically Controlled Stochastic Gradient AISTATS 2017 Mean Field Residual Networks: On the Edge of Chaos NeurIPS 2017 meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting ICML 2017 Model Accuracy and Runtime Tradeoff in Distributed Deep Learning: A Systematic Study IJCAI 2017 More Is Less: A More Complicated Network With Less Inference Complexity CVPR 2017 Multiple-Weight Recurrent Neural Networks IJCAI 2017 Neural Optimizer Search with Reinforcement Learning ICML 2017 Node Pruning Based on Entropy of Weights and Node Activity for Small-Footprint Acoustic Model Based on Deep Neural Networks Interspeech 2017 Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation CVPR 2017 Nonlinear Acceleration of Stochastic Algorithms NeurIPS 2017 On Improving Acoustic Models for TORGO Dysarthric Speech Database Interspeech 2017 Online Learning with Local Permutations and Delayed Feedback ICML 2017 On orthogonality and learning recurrent networks with long term dependencies ICML 2017 On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017 Optimal Rates for Multi-pass Stochastic Gradient Methods JMLR 2017 Plan, Attend, Generate: Planning for Sequence-to-Sequence Models NeurIPS 2017 Practical Gauss-Newton Optimisation for Deep Learning ICML 2017 Preventing Gradient Explosions in Gated Recurrent Units NeurIPS 2017 Probabilistic Line Searches for Stochastic Optimization JMLR 2017