neural network optimization

On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning AAAI 2020 On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them NeurIPS 2020 On the Regularization Properties of Structured Dropout CVPR 2020 On the training dynamics of deep networks with L_2 regularization NeurIPS 2020 On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location CVPR 2020 Optimal Policy for Deployment of Machine Learning Models on Energy-Bounded Systems IJCAI 2020 Optimizing Neural Networks via Koopman Operator Theory NeurIPS 2020 Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization Offers Significant Performance and Efficiency Gains AAAI 2020 Orthogonalized SGD and Nested Architectures for Anytime Neural Networks ICML 2020 Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity Maximization CVPR 2020 Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality NeurIPS 2020 Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks ICLR 2020 Parabolic Approximation Line Search for DNNs NeurIPS 2020 PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-Time Execution on Mobile Devices AAAI 2020 Piecewise linear activations substantially shape the loss surfaces of neural networks ICLR 2020 PowerNorm: Rethinking Batch Normalization in Transformers ICML 2020 Predicting Training Time Without Training NeurIPS 2020 Provable Filter Pruning for Efficient Neural Networks ICLR 2020 Pruning from Scratch AAAI 2020 Pure and Spurious Critical Points: a Geometric Study of Linear Networks ICLR 2020 RandAugment: Practical Automated Data Augmentation with a Reduced Search Space NeurIPS 2020 Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate NeurIPS 2020 Regularization on Spatio-Temporally Smoothed Feature for Action Recognition CVPR 2020 Regularized linear autoencoders recover the principal components, eventually NeurIPS 2020 Regularizing Neural Networks via Minimizing Hyperspherical Energy CVPR 2020