ml:theory:regret_bounds
This is an old revision of the document!
Table of Contents
Theory: Online Learning and Regret Bounds
Online Learning
Surveys and Theses
Regret Bounds
Regret bounds are widely used for proving generalization bounds for online learning algorithms, and for proving convergence rates of optimization algorithms (for example, in the Adagrad paper).
Quick technical explaination from Bottou et al 2016, page 39:
Related Pages
ml/theory/regret_bounds.1652084521.txt.gz · Last modified: 2023/06/15 07:36 (external edit)