Neural Network Optimization

Comparing Rewinding and Fine-tuning in Neural Network Pruning ICLR 2020 Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval NeurIPS 2020 Complexity Guarantees for Polyak Steps with Momentum COLT 2020 Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions ICML 2020 Compositionality and Capacity in Emergent Languages ACL 2020 Computation Reallocation for Object Detection ICLR 2020 Conformal Symplectic and Relativistic Optimization NeurIPS 2020 Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks ICML 2020 Context-Aware Cross-Attention for Non-Autoregressive Translation COLING 2020 Controllable Orthogonalization in Training DNNs CVPR 2020 ConvBERT: Improving BERT with Span-based Dynamic Convolution NeurIPS 2020 Convergence Rates for the Stochastic Gradient Descent Method for Non-Convex Objective Functions JMLR 2020 Convergence Rates of a Momentum Algorithm with Bounded Adaptive Step Size for Nonconvex Optimization ACML 2020 Cooperative Initialization based Deep Neural Network Training WACV 2020 CP-NAS: Child-Parent Neural Architecture Search for 1-bit CNNs IJCAI 2020 Critical initialisation in continuous approximations of binary neural networks ICLR 2020 CSER: Communication-efficient SGD with Error Reset NeurIPS 2020 CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion AAAI 2020 Curriculum Learning by Dynamic Instance Hardness NeurIPS 2020 Curvature-corrected learning dynamics in deep neural networks ICML 2020 DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference ACL 2020 Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control CoRL 2020 Deep Symbolic Superoptimization Without Human Knowledge ICLR 2020 Designing Network Design Spaces CVPR 2020 Differentiable Adaptive Computation Time for Visual Reasoning CVPR 2020