AI Paper Atlas

Research map / Bandits and online learning / Contextual bandits and Thompson sampling

Contextual bandits with surrogate losses: Margin bounds and efficient algorithms

Dylan J Foster, Akshay Krishnamurthy

NeurIPS 2018 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Oracle-efficient contextual bandits · 9 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 ramp loss with sequential metric entropy rather than a pointwise coverAdversarial contextual bandits · Lipschitz contextual banditsregret exponent: \otil(T^{\frac{p+2}{p+4}\vee\frac{p}{p+1}}) versus \otil(T^{\frac{p+1}{p+2}})Improved
Use hinge loss with Hinge-LMC samplingHinge-LMC · Bandit multiclass predictionmistake bound: \otil((B/\gamma)\sqrt{dT})Improved
Use SmoothFTL for stochastic Lipschitz contextual banditsSmoothFTL · Stochastic Lipschitz contextual banditsregret exponent: T^{\frac{p}{p+1}} versus T^{\frac{p+1}{p+2}}Improved
Use hinge loss as the surrogate and its induced action distributionHinge-LMC · Parametric contextual banditsregret: \otil\left(\frac{B}{\gamma}\sqrt{dT}\right)Improved

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