Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

A Survey of Algorithms and Analysis for Adaptive Online Learning

About

We present tools for the analysis of Follow-The-Regularized-Leader (FTRL), Dual Averaging, and Mirror Descent algorithms when the regularizer (equivalently, prox-function or learning rate schedule) is chosen adaptively based on the data. Adaptivity can be used to prove regret bounds that hold on every round, and also allows for data-dependent regret bounds as in AdaGrad-style algorithms (e.g., Online Gradient Descent with adaptive per-coordinate learning rates). We present results from a large number of prior works in a unified manner, using a modular and tight analysis that isolates the key arguments in easily re-usable lemmas. This approach strengthens pre-viously known FTRL analysis techniques to produce bounds as tight as those achieved by potential functions or primal-dual analysis. Further, we prove a general and exact equivalence between an arbitrary adaptive Mirror Descent algorithm and a correspond- ing FTRL update, which allows us to analyze any Mirror Descent algorithm in the same framework. The key to bridging the gap between Dual Averaging and Mirror Descent algorithms lies in an analysis of the FTRL-Proximal algorithm family. Our regret bounds are proved in the most general form, holding for arbitrary norms and non-smooth regularizers with time-varying weight.

H. Brendan McMahan• 2014

Related benchmarks

TaskDatasetResultRank
Question AnsweringARC Challenge--
749
Question AnsweringARC Easy
Accuracy85.9
386
Question AnsweringHotpotQA
Mean Per-Step Regret0.188
15
Truthful Question AnsweringTruthfulQA
Mean Per-Step Regret0.138
15
Question AnsweringSciQ Abstract
Mean per-step regret0.149
15
Rewrite Selection16 QA Datasets Aggregate
Adjusted Metric Value799.6
15
Question AnsweringARC Challenge
Mean Per-Step Regret0.106
15
Question AnsweringOpenBookQA
Mean Per-Step Regret0.177
15
Multiple-choice Question AnsweringTruthfulQA MC
Mean Per-Step Regret0.139
15
Physical Commonsense ReasoningPIQA
Mean Per-Step Regret0.192
15
Showing 10 of 17 rows

Other info

Follow for update