AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Strategic Apple Tasting

Keegan Harris, Chara Podimata, Steven Wu

NeurIPS 2023 · Bandits and online learning › Online convex optimization and games · approach: Online decision-making with feedback structure · 1 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
Shift the linear policy to account for strategic behavior and learn only from clean datagreedy linear policy · strategic classification with apple tasting feedback, stochastic contextsstrategic regret boundImproved
Learn from clean data only under one-sided feedbackgreedy algorithm · strategic classification with apple tasting feedbackstrategic regret boundHurt
Replace the greedy algorithm with strategy-aware explore-then-commitgreedy algorithm · strategic classification with apple tasting feedback, small or unknown Tstrategic regret bound: d * T^{2/3} strategic regretImproved
Combine greedy and explore-then-commit with a doubling trickboth algorithms · strategic classification with apple tasting feedback, unknown Tstrategic regret bound: min{c(d, delta) sqrt(T), d T^{2/3}}Improved
Run EXP3 over a discretized grid of strategy-aware policiesadversarial agent contexts · strategic classification with apple tasting feedback, adversarial contextsstrategic regret bound: T^{(d+1)/(d+2)} strategic regretImproved
Adversarial instead of stochastic contextsapple tasting algorithms · strategic classification with apple tasting feedbackstrategic regret bound: T^{(d+1)/(d+2)} vs sqrt(T)Hurt
Overestimate the manipulation parameter deltagreedy algorithm · strategic classification with apple tasting feedbackstrategic regret boundHurt
Extend one-sided feedback to bandit feedback with unknown r(0)all algorithms · strategic classification with apple tasting feedbackstrategic regret boundNo clear effect

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