AI Paper Atlas

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

Trading Off Resource Budgets For Improved Regret Bounds

Thomas Orton, Damon Falck

NeurIPS 2022 · Bandits and online learning › Online convex optimization and games · approach: Best-of-both-worlds bandit algorithms · 0 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
increase FPML-partial subroutine budget B-tilde from 1 to 2 in OG_hybrid (B=6) (ablation)OG_hybrid · Online HPO, B=6mean reward: 0.785 -> 0.814Improved
increase B-tilde from 2 to 3 in OG_hybrid (B=6) (ablation)OG_hybrid · Online HPO, B=6mean reward: 0.814 -> 0.836Improved
increase B-tilde from 1 to 2 in OG_hybrid (B=4) (ablation)OG_hybrid · Online HPO, B=4mean reward: 0.716 -> 0.756Improved
replace OG's Exp3 subroutine with FPML-partial(3) in hybrid (B=6)OG · Online HPO, B=6mean reward: 0.767 -> 0.836Improved
replace OG's Exp3 subroutine with FPML-partial(2) in hybrid (B=4)OG · Online HPO, B=4mean reward: 0.689 -> 0.756Improved
use FPML-partial(6) instead of OG (B=6)OG · Online HPO, B=6mean reward: 0.767 -> 0.888Improved
use FPML-partial(4) instead of OG(4)OG · Online HPO, B=4mean reward: 0.689 -> 0.813Improved
use OG_hybrid(B,1) instead of OG (different single-arm subroutine, FPML-partial(1) vs Exp3)OG · Online HPO, B=6mean reward: 0.767 -> 0.785No clear effect
use OG_hybrid(4,1) instead of OG(4)OG · Online HPO, B=4mean reward: 0.689 -> 0.716No clear effect
FPML-partial(6) versus best fixed subset of 6 in hindsightBIH(6) · Online HPO, B=6mean reward: 0.901 -> 0.888Hurt
FPML-partial(4) versus best fixed subset of 4 in hindsightBIH(4) · Online HPO, B=4mean reward: 0.836 -> 0.813Hurt
lower budget from B=6 to B=4 for FPML-partial (ablation)FPML-partial · Online HPOmean reward: 0.888 -> 0.813Hurt

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