Online mirror descent and dual averaging: keeping pace in the dynamic
case

v1v2v3 (latest)

Online mirror descent and dual averaging: keeping pace in the dynamic case

3 June 2020

Nicholas J. A. Harvey

ArXiv (abs)PDF HTML

Papers citing "Online mirror descent and dual averaging: keeping pace in the dynamic case"

8 / 8 papers shown

Title
On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning N. Mhaisen George Iosifidis 22 0 0 28 May 2025
Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning Aneesh Muppidi Zhiyu Zhang Heng Yang 78 6 0 26 May 2024
Parameter-free Mirror Descent Andrew Jacobsen Ashok Cutkosky 109 34 0 26 Feb 2022
Isotuning With Applications To Scale-Free Online Learning Laurent Orseau Marcus Hutter 74 6 0 29 Dec 2021
Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization Peng Zhao Yu Zhang Lijun Zhang Zhi Zhou 110 50 0 29 Dec 2021
Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games Weichao Mao Tamer Basar 97 67 0 12 Oct 2021
Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium Yu-Guan Hsieh Kimon Antonakopoulos P. Mertikopoulos 82 77 0 26 Apr 2021
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses Yihan Zhou V. S. Portella Mark Schmidt Nicholas J. A. Harvey 40 21 0 22 Oct 2020