conftrace_

mirror descent

148 papers

Explore in graph

Also known as

MD

Co-occurring keywords

regret bound (1926) convex optimization (1321) online learning (1777) stochastic optimization (1060) gradient descent (1144) reinforcement learning (4352) bregman divergence (81) policy gradient (520) policy optimization (657) online convex optimization (165)

Papers

Accelerated Mirror Descent for Non-Euclidean Star-convex Functions ALT 2026
Methods for Optimization Problems with Markovian Stochasticity and Non-Euclidean Geometry AAAI 2026
Designing Algorithms for Entropic Optimal Transport from an Optimisation Perspective ALT 2026
Last-iterate Convergence in Regularized Graphon Mean Field Game AAAI 2025
Gradient Equilibrium in Online Learning: Theory and Applications JMLR 2025
Implicit Bias of Mirror Flow on Separable Data NIPS 2024
Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning EMNLP 2024
Learning Bregman Divergences with Application to Robustness NIPS 2024
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation NIPS 2024
Policy Mirror Descent with Lookahead NIPS 2024
Policy Optimization for Robust Average Reward MDPs NIPS 2024
Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds JMLR 2024
Gradient-Variation Online Learning under Generalized Smoothness NIPS 2024
Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems extended abstract COLT 2024
Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithm COLT 2024
Noisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource Allocation NIPS 2024
Sinkhorn Flow as Mirror Flow: A Continuous-Time Framework for Generalizing the Sinkhorn Algorithm AISTATS 2024
Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation CVPR 2024
Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition NIPS 2024
Mirror and Preconditioned Gradient Descent in Wasserstein Space NIPS 2024
On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games NIPS 2024
Online Composite Optimization Between Stochastic and Adversarial Environments NIPS 2024
HyperPrism: An Adaptive Non-linear Aggregation Framework for Distributed Machine Learning over Non-IID Data and Time-varying Communication Links NIPS 2024
Local and Adaptive Mirror Descents in Extensive-Form Games NIPS 2024
Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent AISTATS 2024