Research map / Bandits and online learning / Multi-armed bandits
Fiduciary Bandits
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use EAIR-constrained exploration followed by exploitation of the best observed arm | FEE in the fiduciary bandit model with non-strategic agents · Fiduciary bandit model | social welfare: SW_{n}(\textnormal{FEE}) \geq \OPTEA-O\left(\frac{KH^2}{n} \right) | Helped |
| Add randomized exploration phases and IC recommendations to FEE | FEE for strategic agents · Fiduciary bandit model | social welfare: SW_{n}(\textnormal{IC-FEE}) \geq \OPTEA-O\left(\frac{KH^3}{n\xi \gamma} \right) | Helped |
| Impose EAIR rather than leaving welfare unconstrained | Fiduciary bandit mechanisms · Fiduciary bandit model | welfare ratio: \frac{\textnormal{OPT}}{\OPTEA} \geq H\left(1-e^{-\frac{K}{H}}\right) | Hurt |
| Replace EAIR with the stricter EPIR guarantee | Fiduciary bandit mechanisms · Fiduciary bandit model | welfare ratio: \frac{\OPTEA}{\OPTEP} \geq \frac{H+2}{3}\left(1-e^{-\frac{K-2}{H}} \right) | Hurt |
| Allow EPIR exploration rather than requiring delegate-greedy recommendations | Fiduciary bandit mechanisms · Fiduciary bandit model | welfare ratio: \frac{\OPTEP}{\OPTDEL} \geq \frac{H}{3}\left( 1-e^{-\frac{K-2}{H}}\right) | Helped |
Closest papers by meaning
- Incentivized Exploration with Stochastic Covariates: A Two-Stage Mechanism Design for Recommender System (ICML 2026 · similarity 0.90)
- Learning the Optimal Recommendation from Explorative Users (AAAI 2022 · similarity 0.89)
- Learning to Recommend in Unknown Games (NeurIPS 2026 · similarity 0.87)
- Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation (ICLR 2024 · similarity 0.86)
- Recommender Ecosystems: A Mechanism Design Perspective on Holistic Modeling and Optimization (AAAI 2024 · similarity 0.86)
- Strategic Linear Contextual Bandits (NeurIPS 2024 · similarity 0.85)
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.