neural network optimization

AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates AAAI 2020 AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning NeurIPS 2020 Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods NeurIPS 2020 Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness ICLR 2020 Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints ICLR 2020 Butterfly Transform: An Efficient FFT Based Neural Architecture Design CVPR 2020 Channel Pruning Guided by Classification Loss and Feature Importance AAAI 2020 Confidence-Aware Learning for Deep Neural Networks ICML 2020 Continual Learning With Extended Kronecker-Factored Approximate Curvature CVPR 2020 Controllable Orthogonalization in Training DNNs CVPR 2020 Critical initialisation in continuous approximations of binary neural networks ICLR 2020 Curriculum Learning by Dynamic Instance Hardness NeurIPS 2020 DMCP: Differentiable Markov Channel Pruning for Neural Networks CVPR 2020 DropNAS: Grouped Operation Dropout for Differentiable Architecture Search IJCAI 2020 DWM: A Decomposable Winograd Method for Convolution Acceleration AAAI 2020 Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change ACL 2020 Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families AAAI 2020 Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference CVPR 2020 Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives CVPR 2020 Effect of Activation Functions on the Training of Overparametrized Neural Nets ICLR 2020 Efficient Proximal Mapping of the 1-path-norm of Shallow Networks ICML 2020 Emergence of functional and structural properties of the head direction system by optimization of recurrent neural networks ICLR 2020 Escaping the Gravitational Pull of Softmax NeurIPS 2020 Exactly Computing the Local Lipschitz Constant of ReLU Networks NeurIPS 2020 ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks NeurIPS 2020