variance reduction

Dual Critic Reinforcement Learning under Partial Observability NeurIPS 2024 Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond ICML 2024 Efficient Backpropagation with Variance Controlled Adaptive Sampling ICLR 2024 Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design ICML 2024 Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction NeurIPS 2024 Efficient Training of Language Models with Compact and Consistent Next Token Distributions ACL 2024 Fast and unified path gradient estimators for normalizing flows ICLR 2024 Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization AAAI 2024 GGD: Grafting Gradient Descent JMLR 2024 Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games ICML 2024 Infeasible Deterministic, Stochastic, and Variance-Reduction Algorithms for Optimization under Orthogonality Constraints JMLR 2024 Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization AAAI 2024 Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction ICLR 2024 Momentum Benefits Non-iid Federated Learning Simply and Provably ICLR 2024 Nearest Neighbour Score Estimators for Diffusion Generative Models ICML 2024 Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity NeurIPS 2024 New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions ICLR 2024 Non-convex Stochastic Composite Optimization with Polyak Momentum ICML 2024 On Differentially Private U Statistics NeurIPS 2024 On Divergence Measures for Training GFlowNets NeurIPS 2024 One Forward is Enough for Neural Network Training via Likelihood Ratio Method ICLR 2024 Precise Model Benchmarking with Only a Few Observations EMNLP 2024 Prior-dependent analysis of posterior sampling reinforcement learning with function approximation AISTATS 2024 PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds IJCAI 2024 Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization ICML 2024