English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose the Generalized Policy Elimination (GPE) algorithm, anoracle-efficient contextual bandit (CB) algorithm inspired by the PolicyElimination algorithm of \cite{dudik2011}. We prove the first regret optimalityguarantee theorem for an oracle-efficient CB algorithm competing against anonparametric class with infinite VC-dimension. Specifically, we show that GPEis regret-optimal (up to logarithmic factors) for policy classes withintegrable entropy. For classes with larger entropy, we show that the coretechniques used to analyze GPE can be used to design an $\varepsilon$-greedyalgorithm with regret bound matching that of the best algorithms to date. Weillustrate the applicability of our algorithms and theorems with examples oflarge nonparametric policy classes, for which the relevant optimization oraclescan be efficiently implemented.

Generalized Policy Elimination: an efficient algorithm for Nonparametric Contextual Bandits