Neural Network Optimization

Orthogonal Convolutional Neural Networks CVPR 2020 Orthogonalized SGD and Nested Architectures for Anytime Neural Networks ICML 2020 Overcoming Catastrophic Forgetting by Neuron-Level Plasticity Control AAAI 2020 Overflow Aware Quantization: Accelerating Neural Network Inference by Low-bit Multiply-Accumulate Operations IJCAI 2020 Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality NeurIPS 2020 Parabolic Approximation Line Search for DNNs NeurIPS 2020 pbSGD: Powered Stochastic Gradient Descent Methods for Accelerated Non-Convex Optimization IJCAI 2020 PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search ICLR 2020 Picking Winning Tickets Before Training by Preserving Gradient Flow ICLR 2020 Piecewise linear activations substantially shape the loss surfaces of neural networks ICLR 2020 Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP ICLR 2020 Porous Lattice Transformer Encoder for Chinese NER COLING 2020 Position-based Scaled Gradient for Model Quantization and Pruning NeurIPS 2020 PowerNorm: Rethinking Batch Normalization in Transformers ICML 2020 Practical Quasi-Newton Methods for Training Deep Neural Networks NeurIPS 2020 Predicting Training Time Without Training NeurIPS 2020 Principled Weight Initialization for Hypernetworks ICLR 2020 Projection & Probability-Driven Black-Box Attack CVPR 2020 Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks ICLR 2020 Provably Efficient Exploration in Policy Optimization ICML 2020 Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach NeurIPS 2020 Provably Efficient Neural GTD for Off-Policy Learning NeurIPS 2020 Proving the Lottery Ticket Hypothesis: Pruning is All You Need ICML 2020 Proximal Gradient Algorithm with Momentum and Flexible Parameter Restart for Nonconvex Optimization IJCAI 2020 Proximal Mapping for Deep Regularization NeurIPS 2020