Neural Network Optimization

Deep Layers as Stochastic Solvers ICLR 2019 Dynamic Recursive Neural Network CVPR 2019 Efficient Diversified Mini-Batch Selection using Variable High-layer Features ACML 2019 Efficient Forward Architecture Search NeurIPS 2019 Efficiently testing local optimality and escaping saddles for ReLU networks ICLR 2019 Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron AISTATS 2019 FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search CVPR 2019 Fine-grained Optimization of Deep Neural Networks NeurIPS 2019 Generalized Batch Normalization: Towards Accelerating Deep Neural Networks AAAI 2019 Global Sparse Momentum SGD for Pruning Very Deep Neural Networks NeurIPS 2019 Guided Dropout AAAI 2019 HyperAdam: A Learnable Task-Adaptive Adam for Network Training AAAI 2019 Initialization of ReLUs for Dynamical Isometry NeurIPS 2019 Inter-Class Angular Loss for Convolutional Neural Networks AAAI 2019 IRLAS: Inverse Reinforcement Learning for Architecture Search CVPR 2019 Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation CVPR 2019 Learning Anytime Predictions in Neural Networks via Adaptive Loss Balancing AAAI 2019 Learning Dynamic Generator Model by Alternating Back-Propagation through Time AAAI 2019 Learning in the Machine: Random Backpropagation and the Deep Learning Channel (Extended Abstract) IJCAI 2019 Making Asynchronous Stochastic Gradient Descent Work for Transformers EMNLP 2019 MnasNet: Platform-Aware Neural Architecture Search for Mobile CVPR 2019 MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation CVPR 2019 Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization CVPR 2019 One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers NeurIPS 2019 On Implicit Filter Level Sparsity in Convolutional Neural Networks CVPR 2019