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 design and analyze CascadeBAI, an algorithm for finding the best set of$K$ items, also called an arm, within the framework of cascading bandits. Anupper bound on the time complexity of CascadeBAI is derived by overcoming acrucial analytical challenge, namely, that of probabilistically estimating theamount of available feedback at each step. To do so, we define a new class ofrandom variables (r.v.'s) which we term as left-sided sub-Gaussian r.v.'s;these are r.v.'s whose cumulant generating functions (CGFs) can be bounded by aquadratic only for non-positive arguments of the CGFs. This enables theapplication of a sufficiently tight Bernstein-type concentration inequality. Weshow, through the derivation of a lower bound on the time complexity, that theperformance of CascadeBAI is optimal in some practical regimes. Finally,extensive numerical simulations corroborate the efficacy of CascadeBAI as wellas the tightness of our upper bound on its time complexity.

Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting