AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Online Frank-Wolfe with Arbitrary Delays

Yuanyu Wan, Wei-Wei Tu, Lijun Zhang

NeurIPS 2022 · Bandits and online learning › Online convex optimization and games · approach: Constrained and unconstrained OCO algorithms · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use delayed OFW (update on each delayed gradient, play latest decision) instead of BOLD black-box with multiple OFW instances, convex lossesDOFW vs BOLD-OFW · Simulated delayed OCO, T=10000, 1000-dim l1 ball, d in {51,...,501}total lossImproved
use delayed OFW for strongly convex losses instead of BOLD-OFWscDOFWsc vs BOLD-OFWsc · Simulated delayed OCO, d = 501cumulative lossImproved
no delay (d = 1) comparing DOFW to BOLD-OFWDOFW, DOFWsc · Simulated delayed OCOtotal lossNo clear effect
increase maximum delay d from 1 to 501DOFW, DOFWsc · Simulated delayed OCOtotal lossHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy