Power-Constrained Bandits

04/13/2020
by   Jiayu Yao, et al.
1

Contextual bandits often provide simple and effective personalization in decision making problems, making them popular in many domains including digital health. However, when bandits are deployed in the context of a scientific study, the aim is not only to personalize for an individual, but also to determine, with sufficient statistical power, whether or not the system's intervention is effective. In this work, we develop a set of constraints and a general meta-algorithm that can be used to both guarantee power constraints and minimize regret. Our results demonstrate a number of existing algorithms can be easily modified to satisfy the constraint without significant decrease in average return. We also show that our modification is also robust to a variety of model mis-specifications.

READ FULL TEXT
research
10/21/2022

Anonymous Bandits for Multi-User Systems

In this work, we present and study a new framework for online learning i...
research
04/27/2015

Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits

We study contextual bandits with budget and time constraints, referred t...
research
10/24/2022

Conditionally Risk-Averse Contextual Bandits

We desire to apply contextual bandits to scenarios where average-case st...
research
03/29/2022

Stochastic Conservative Contextual Linear Bandits

Many physical systems have underlying safety considerations that require...
research
01/19/2023

Decision-Focused Evaluation: Analyzing Performance of Deployed Restless Multi-Arm Bandits

Restless multi-arm bandits (RMABs) is a popular decision-theoretic frame...
research
06/07/2021

Generalized Linear Bandits with Local Differential Privacy

Contextual bandit algorithms are useful in personalized online decision-...
research
10/15/2019

Adaptive Exploration in Linear Contextual Bandit

Contextual bandits serve as a fundamental model for many sequential deci...

Please sign up or login with your details

Forgot password? Click here to reset