AI Paper Atlas

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

Beyond Bandit Feedback in Online Multiclass Classification

Dirk van der Hoeven, Federico Fusco, Nicolò Cesa-Bianchi

NeurIPS 2021 · Bandits and online learning › Online convex optimization and games · approach: Online learning with feedback graphs · 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 GapHin (hinge loss) instead of GapLog or GapSmH (ablation)Gappletron · synthetic bandit settingerror rate stabilityHurt
use logistic loss (GapLog) instead of hinge or smooth hinge (ablation)Gappletron · synthetic multiclass spam filtering, K > 6mistakesHurt
use logistic loss (GapLog) instead of hinge or smooth hinge (ablation)Gappletron · synthetic bandit settingrange of error rate over repetitionsImproved
increase the exploration rate (ablation)Gappletron · synthetic data, all settingsstability of error rateImproved
use Gappletron instead of PNewtron, SOBAdiag and importance weighted Banditrononline multiclass classifier · synthetic bandit settingerror rateImproved
restrict label requests to the revealing action (label efficient feedback graph, rho=1) instead of bandit feedback (rho=K)Gappletron surrogate regret bound · theorysurrogate regret boundImproved

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