AI Paper Atlas

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

Luckiness in Multiscale Online Learning

Wouter M Koolen, Muriel Felipe Pérez

NeurIPS 2022 · Bandits and online learning › Online convex optimization and games · approach: Last-iterate convergence in games · 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
run MUSCADA on i.i.d. data satisfying Massart's condition (lambda_2 = -1/5) instead of gap-free dataMUSCADA (Tuning 1/2) · Synthetic experts, K=50, sigma_k=1/kregret of best expert R_t,k*Improved
hard stochastic data with no gap (all lambda_k = 0)MUSCADA · Synthetic experts, K=50, sigma_k=1/kregret growthHurt
add optimism (guess of next losses) to MUSCADA and play two instances against each otherOptimistic MUSCADA · Multiscale zero-sum game, sigma_max/100 relevant scaleiterate-average saddle-point gapImproved
remove optimism from MUSCADA in multiscale games (ablation)MUSCADA (non-optimistic) · Multiscale zero-sum gamesaddle-point gap rateHurt
use multiscale-aware MUSCADA instead of single-scale algorithms in games with multiscale payoffsOptimistic MUSCADA · Multiscale zero-sum gameconvergence to saddle pointImproved

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