Logarithmic Regret for Online Gradient Descent Beyond Strong Convexity

v1v2 (latest)

Logarithmic Regret for Online Gradient Descent Beyond Strong Convexity

13 February 2018

ArXiv (abs)PDF HTML

Papers citing "Logarithmic Regret for Online Gradient Descent Beyond Strong Convexity"

5 / 5 papers shown

Title
On Corruption-Robustness in Performative Reinforcement Learning Vasilis Pollatos Debmalya Mandal Goran Radanović 190 2 0 08 May 2025
Introduction to Online Convex Optimization Elad Hazan OffRL 193 1,940 0 07 Sep 2019
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition Hamed Karimi J. Nutini Mark Schmidt 280 1,221 0 16 Aug 2016
Efficient Second Order Online Learning by Sketching Haipeng Luo Alekh Agarwal Nicolò Cesa-Bianchi John Langford 81 96 0 06 Feb 2016
A simpler approach to obtaining an O(1/t) convergence rate for the projected stochastic subgradient method Simon Lacoste-Julien Mark Schmidt Francis R. Bach 190 261 0 10 Dec 2012