AI Paper Atlas

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

Minimax Regret for Cascading Bandits

Daniel Vial, sujay sanghavi, Sanjay Shakkottai, R. Srikant

NeurIPS 2022 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Causal and structured bandits · 2 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 CascadeUCB-V instead of CascadeKL-UCBTabular cascading bandits · Tabular cascading banditsregretHurt
Use CascadeUCB-V instead of CascadeKL-UCBTabular cascading bandits · Tabular cascading banditscomputation timeImproved
Use CascadeWOFUL instead of CascadeLinUCBLinear cascading bandits · Synthetic dataregretImproved
Use CascadeWOFUL instead of CascadeLinUCBLinear cascading bandits · MovieLens-1Mregret: less than 66%Improved
Use CascadeWOFUL instead of CascadeLinUCBLinear cascading bandits · MovieLens-1M genre subsetsregret: about halfImproved
Use variance-aware rather than variance-unaware UCBsTabular cascading bandits · Synthetic data, varying Kregret dependence on KImproved
Use CascadeWOFUL rather than CascadeLinUCB, especially at lower click-through ratesLinear cascading bandits · MovieLens-1M genre subsetsregretImproved

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