variance reduction

Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension ICML 2025 Doubly Optimal Policy Evaluation for Reinforcement Learning ICLR 2025 EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback JMLR 2025 Efficiently Escaping Saddle Points for Policy Optimization UAI 2025 Efficient Multi-Policy Evaluation for Reinforcement Learning AAAI 2025 Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning ICLR 2025 Faster Double Adaptive Gradient Methods AAAI 2025 Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost ICLR 2025 Federated Stochastic Bilevel Optimization with Fully First-Order Gradients IJCAI 2025 Instance-level Randomization: Toward More Stable LLM Evaluations EMNLP 2025 Learning Robust Neural Processes with Risk-Averse Stochastic Optimization ICML 2025 Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation CoRL 2025 MARS: Unleashing the Power of Variance Reduction for Training Large Models ICML 2025 MAST: model-agnostic sparsified training ICLR 2025 Minimal Variance Model Aggregation: A principled, non-intrusive, and versatile integration of black box models ICLR 2025 Nearly Optimal Sample Complexity for Learning with Label Proportions ICML 2025 Optimal Complexity in Byzantine-Robust Distributed Stochastic Optimization with Data Heterogeneity JMLR 2025 Optimal Stochastic Trace Estimation in Generative Modeling AISTATS 2025 Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs AISTATS 2025 QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions ICML 2025 Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games ICML 2025 Refining Adaptive Zeroth-Order Optimization at Ease ICML 2025 Revisiting Fairness in Multitask Learning: A Performance-Driven Approach for Variance Reduction CVPR 2025 Revisiting Large-Scale Non-convex Distributionally Robust Optimization ICLR 2025 SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization ICML 2025