mirror descent

Mirror and Preconditioned Gradient Descent in Wasserstein Space NeurIPS 2024 Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems extended abstract COLT 2024 Nash Learning from Human Feedback ICML 2024 Noisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource Allocation NeurIPS 2024 Online Composite Optimization Between Stochastic and Adversarial Environments NeurIPS 2024 On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games NeurIPS 2024 Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning EMNLP 2024 Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition NeurIPS 2024 Policy Mirror Descent with Lookahead NeurIPS 2024 Policy Optimization for Robust Average Reward MDPs NeurIPS 2024 Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds JMLR 2024 Sinkhorn Flow as Mirror Flow: A Continuous-Time Framework for Generalizing the Sinkhorn Algorithm AISTATS 2024 Synaptic Weight Distributions Depend on the Geometry of Plasticity ICLR 2024 Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation CVPR 2024 Accelerated Primal-Dual Mirror Dynamics for Centralized and Distributed Constrained Convex Optimization Problems JMLR 2023 A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence NeurIPS 2023 A Unified Approach to Controlling Implicit Regularization via Mirror Descent JMLR 2023 Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games ICLR 2023 Faster Margin Maximization Rates for Generic Optimization Methods NeurIPS 2023 Generalized Implicit Follow-The-Regularized-Leader ICML 2023 Gradient-Variation Bound for Online Convex Optimization with Constraints AAAI 2023 Implicit Regularization for Group Sparsity ICLR 2023 Improved Rate of First Order Algorithms for Entropic Optimal Transport AISTATS 2023 Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation ICML 2023 Mirror Sinkhorn: Fast Online Optimization on Transport Polytopes ICML 2023