AI Paper Atlas

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

Differentially Private Contextual Linear Bandits

Roshan Shariff, Or Sheffet

NeurIPS 2018 · Bandits and online learning › Contextual bandits and Thompson sampling · approach: Oracle-efficient contextual bandits · 51 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 standard differential privacy instead of joint differential privacyContextual bandits · Contextual bandits under continual observationpseudo-regretHurt
Use joint differential privacy with tree-based private history and LinUCBContextual linear bandits · Contextual linear banditspseudo-regretImproved
Use Wishart noise rather than Gaussian noiseTree-based private LinUCB · Contextual linear banditspseudo-regret bound dependence on εMixed
Add a gap assumption separating optimal and suboptimal actionsChanging-regularizer LinUCB · Contextual linear bandits with reward gap Δpseudo-regret boundImproved
Require private MAB algorithms to preserve ε-differential privacyMAB algorithms · Stochastic MABadditional pseudo-regretHurt

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