variance reduction

Stochastic Reweighted Gradient Descent ICML 2022 Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions NeurIPS 2022 Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability CVPR 2022 Stochastic Variance Reduction for Variational Inequality Methods COLT 2022 Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology ICML 2022 The Role of Baselines in Policy Gradient Optimization NeurIPS 2022 Towards Optimal Communication Complexity in Distributed Non-Convex Optimization NeurIPS 2022 Training Discrete Deep Generative Models via Gapped Straight-Through Estimator ICML 2022 Training Structured Neural Networks Through Manifold Identification and Variance Reduction ICLR 2022 Truncated Emphatic Temporal Difference Methods for Prediction and Control JMLR 2022 Variance Reduced EXTRA and DIGing and Their Optimal Acceleration for Strongly Convex Decentralized Optimization JMLR 2022 Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning NeurIPS 2022 Zero-shot Cross-lingual Transfer is Under-specified Optimization ACL 2022 Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance Reduction ICLR 2021 A comparative study on sampling with replacement vs Poisson sampling in optimal subsampling AISTATS 2021 A Faster Decentralized Algorithm for Nonconvex Minimax Problems NeurIPS 2021 A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization ICML 2021 A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! AISTATS 2021 An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders NeurIPS 2021 ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables ICML 2021 Beyond Variance Reduction: Understanding the True Impact of Baselines on Policy Optimization ICML 2021 Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning ICML 2021 Black-Box Reductions for Zeroth-Order Gradient Algorithms to Achieve Lower Query Complexity JMLR 2021 Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning NeurIPS 2021 CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator NeurIPS 2021