AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Polynomial Cost of Adaptation for X-Armed Bandits

Hedi Hadiji

NeurIPS 2019 · Bandits and online learning › Multi-armed bandits · approach: Optimal stochastic bandit algorithms · 4 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 MeDZO to adapt to unknown Hölder regularity with input BContinuum-armed bandits · Hölder cumulative regret, known horizonexpected cumulative regret: 412 \, (\log_2 B)^{3/2} \max \big( B , \, T L^{1/(\alpha + 1) }B^{-\alpha / (\alpha + 1)} \, \big)Improved
Tune the anytime MeDZO input to mMeDZO · Hölder cumulative regret, unknown smoothnessregret rate exponent: {\mathcal O} \big( (\log T)^{3/2}\, T^{\theta_m(\alpha)}\big)Improved
Set B = \sqrt TMeDZO · Hölder cumulative regretexpected cumulative regret: 146 \, (\log_2 T )^{3/2} \, L^{1 / (\alpha + 1)}\, T^{(\alpha +2)/(2\alpha + 2)}Improved
Use GPO cross-validation among candidate discretizationsGPO with CAB1.1 · Hölder simple regret, unknown smoothnesssimple regret: \big(54 + \frac{\sqrt{\pi}}{2} \log_2 T \big) L^{1 / (2\alpha +1)} \bigg(\frac{\ceil{\log_2 T}}{T}\bigg)^{\alpha / (2\alImproved
Adapt to Hölder smoothness for cumulative rather than simple regretContinuum-armed bandits · Hölder cumulative regretregret rate: L^{1/(1+ \alpha)} T^{(\alpha + 2)/(2\alpha + 2)}Mixed

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