stochastic gradient descent

On the universality of deep learning NeurIPS 2020 Open Problem: Tight Convergence of SGD in Constant Dimension COLT 2020 Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization NeurIPS 2020 Optimization Methods for Interpretable Differentiable Decision Trees Applied to Reinforcement Learning AISTATS 2020 Optimizing Millions of Hyperparameters by Implicit Differentiation AISTATS 2020 Orthogonalized SGD and Nested Architectures for Anytime Neural Networks ICML 2020 pbSGD: Powered Stochastic Gradient Descent Methods for Accelerated Non-Convex Optimization IJCAI 2020 PEP: Parameter Ensembling by Perturbation NeurIPS 2020 Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks ICLR 2020 Predicting Training Time Without Training NeurIPS 2020 Privacy Amplification via Random Check-Ins NeurIPS 2020 ProxSGD: Training Structured Neural Networks under Regularization and Constraints ICLR 2020 Quantitative Propagation of Chaos for SGD in Wide Neural Networks NeurIPS 2020 Quantized Compressive Sampling of Stochastic Gradients for Efficient Communication in Distributed Deep Learning AAAI 2020 Random Reshuffling is Not Always Better NeurIPS 2020 Random Reshuffling: Simple Analysis with Vast Improvements NeurIPS 2020 Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian NeurIPS 2020 Robust, Accurate Stochastic Optimization for Variational Inference NeurIPS 2020 Robustness Analysis of Non-Convex Stochastic Gradient Descent using Biased Expectations NeurIPS 2020 Scalable Differential Privacy with Certified Robustness in Adversarial Learning ICML 2020 SGD Learns One-Layer Networks in WGANs ICML 2020 SGD with shuffling: optimal rates without component convexity and large epoch requirements NeurIPS 2020 SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum ICLR 2020 Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses NeurIPS 2020 Stochastic Approximate Gradient Descent via the Langevin Algorithm AAAI 2020