Optimization & Theory

Local Binary Convolutional Neural Networks CVPR 2017 Low-Rank Bilinear Pooling for Fine-Grained Classification CVPR 2017 Massive Exploration of Neural Machine Translation Architectures EMNLP 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 More Is Less: A More Complicated Network With Less Inference Complexity CVPR 2017 Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency CVPR 2017 Natasha: Faster Non-Convex Stochastic Optimization via Strongly Non-Convex Parameter ICML 2017 Net-Trim: Convex Pruning of Deep Neural Networks with Performance Guarantee NeurIPS 2017 Network Sketching: Exploiting Binary Structure in Deep CNNs CVPR 2017 NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks ACML 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 Non-convex Finite-Sum Optimization Via SCSG Methods NeurIPS 2017 Nonlinear random matrix theory for deep learning NeurIPS 2017 OctNet: Learning Deep 3D Representations at High Resolutions CVPR 2017 On Approximation Guarantees for Greedy Low Rank Optimization ICML 2017 On Blackbox Backpropagation and Jacobian Sensing NeurIPS 2017 On Compressing Deep Models by Low Rank and Sparse Decomposition CVPR 2017 One-To-Many Network for Visually Pleasing Compression Artifacts Reduction CVPR 2017 On the Complexity of Learning Neural Networks NeurIPS 2017 On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017 On-the-fly Operation Batching in Dynamic Computation Graphs NeurIPS 2017 On the Learnability of Fully-Connected Neural Networks AISTATS 2017 Optimal Rates for Multi-pass Stochastic Gradient Methods JMLR 2017