stochastic gradient descent

Bounding the expected run-time of nonconvex optimization with early stopping UAI 2020 Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization NeurIPS 2020 Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study NeurIPS 2020 Choosing the Sample with Lowest Loss makes SGD Robust AISTATS 2020 Closing the convergence gap of SGD without replacement ICML 2020 Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks IJCAI 2020 Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization ICLR 2020 Continuous Regularized Wasserstein Barycenters NeurIPS 2020 Convergence Rates for the Stochastic Gradient Descent Method for Non-Convex Objective Functions JMLR 2020 Coresets for Data-efficient Training of Machine Learning Models ICML 2020 CSER: Communication-efficient SGD with Error Reset NeurIPS 2020 Debiasing Averaged Stochastic Gradient Descent to handle missing values NeurIPS 2020 Delay-Adaptive Distributed Stochastic Optimization AAAI 2020 Differentially Private Learning with Small Public Data AAAI 2020 Directional Pruning of Deep Neural Networks NeurIPS 2020 Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms NeurIPS 2020 Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification NeurIPS 2020 Efficient Parameter Estimation of Truncated Boolean Product Distributions COLT 2020 Escaping Saddle-Point Faster under Interpolation-like Conditions NeurIPS 2020 Escaping Saddle Points Faster with Stochastic Momentum ICLR 2020 Estimating Training Data Influence by Tracing Gradient Descent NeurIPS 2020 Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks CVPR 2020 Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling NeurIPS 2020 Extrapolation for Large-batch Training in Deep Learning ICML 2020 Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods ICML 2020