paper-with-me

Papers

Fair Algorithms for Infinite and Contextual Bandits

2016-10-29 · Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel, Aaron Roth

We study fairness in linear bandit problems. Starting from the notion of meritocratic fairness introduced in Joseph et al. [2016], we carry out a more refined analysis of a more general problem, achieving better performance guarantees with fewer modelling assumptions on the number and structure of available choices as well as the number selected. We also analyze the previously-unstudied question of fairness in infinite linear bandit problems, obtaining instance-dependent regret upper bounds as well as lower bounds demonstrating that this instance-dependence is necessary. The result is a framework for meritocratic fairness in an online linear setting that is substantially more powerful, general, and realistic than the current state of the art.

📄 PDF Abstract BibTeX arXiv:1610.09559

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessMulti-Armed Bandits

Similar Papers 제목 키워드 기반

Adapting to Misspecification in Contextual Bandits

2021-07-12 · NeurIPS 2020 12 · Dylan J. Foster, Claudio Gentile, Mehryar Mohri, Julian Zimmert

A major research direction in contextual bandits is to develop algorithms that are computationally efficient, yet support flexible, general-purpose function approximation. Algorithms based on modeling rewards have shown …

Multi-Armed Banditsregression

Contextual bandits with concave rewards, and an application to fair ranking

2022-10-18 · Virginie Do, Elvis Dohmatob, Matteo Pirotta, Alessandro Lazaric 외

We consider Contextual Bandits with Concave Rewards (CBCR), a multi-objective bandit problem where the desired trade-off between the rewards is defined by a known concave objective function, and the reward vector depends…

FairnessMulti-Armed Bandits

Fairness in Learning: Classic and Contextual Bandits

2016-05-23 · NeurIPS 2016 12 · Matthew Joseph, Michael Kearns, Jamie Morgenstern, Aaron Roth

We introduce the study of fairness in multi-armed bandit problems. Our fairness definition can be interpreted as demanding that given a pool of applicants (say, for college admission or mortgages), a worse applicant is n…

FairnessMulti-Armed Bandits

Fairness of Exposure in Stochastic Bandits

2021-03-03 · Lequn Wang, Yiwei Bai, Wen Sun, Thorsten Joachims

Contextual bandit algorithms have become widely used for recommendation in online systems (e.g. marketplaces, music streaming, news), where they now wield substantial influence on which items get exposed to the users. Th…

FairnessMulti-Armed Bandits

Upper Counterfactual Confidence Bounds: a New Optimism Principle for Contextual Bandits

2020-07-15 · Yunbei Xu, Assaf Zeevi

The principle of optimism in the face of uncertainty is one of the most widely used and successful ideas in multi-armed bandits and reinforcement learning. However, existing optimistic algorithms (primarily UCB and its v…

counterfactualMulti-Armed Banditsregression