Optimization

Sideways: Depth-Parallel Training of Video Models CVPR 2020 SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum ICLR 2020 SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization ACL 2020 Soft Threshold Weight Reparameterization for Learnable Sparsity ICML 2020 SPAN: A Stochastic Projected Approximate Newton Method AAAI 2020 Sparsity-Inducing Binarized Neural Networks AAAI 2020 Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error IJCAI 2020 Stochastic Approximate Gradient Descent via the Langevin Algorithm AAAI 2020 Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization ICML 2020 Stochastic Loss Function AAAI 2020 Streaming Batch Gradient Tracking for Neural Network Training (Student Abstract) AAAI 2020 Stronger and Faster Wasserstein Adversarial Attacks ICML 2020 Taylor Expansion Policy Optimization ICML 2020 The EOS Decision and Length Extrapolation EMNLP 2020 TomoFluid: Reconstructing Dynamic Fluid From Sparse View Videos CVPR 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 Training Binary Neural Networks using the Bayesian Learning Rule ICML 2020 Training Deep Energy-Based Models with f-Divergence Minimization ICML 2020 Transferring Optimality Across Data Distributions via Homotopy Methods ICLR 2020 Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems ICML 2020 Understanding the Disharmony between Weight Normalization Family and Weight Decay AAAI 2020 Understanding the Role of Training Regimes in Continual Learning NeurIPS 2020 WCP: Worst-Case Perturbations for Semi-Supervised Deep Learning CVPR 2020 What Deep CNNs Benefit From Global Covariance Pooling: An Optimization Perspective CVPR 2020 X-TaSNet: Robust and Accurate Time-Domain Speaker Extraction Network Interspeech 2020