Power Constrained Bandits

2020-04-13 · Jiayu Yao, Emma Brunskill, Weiwei Pan, Susan Murphy, Finale Doshi-Velez

Contextual bandits often provide simple and effective personalization in decision making problems, making them popular tools to deliver personalized interventions in mobile health as well as other health applications. However, when bandits are deployed in the context of a scientific study -- e.g. a clinical trial to test if a mobile health intervention is effective -- 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. It is essential to assess the effectiveness of the intervention before broader deployment for better resource allocation. The two objectives are often deployed under different model assumptions, making it hard to determine how achieving the personalization and statistical power affect each other. In this work, we develop general meta-algorithms to modify existing algorithms such that sufficient power is guaranteed while still improving each user's well-being. We also demonstrate that our meta-algorithms are robust to various model mis-specifications possibly appearing in statistical studies, thus providing a valuable tool to study designers.

📄 PDF Abstract BibTeX arXiv:2004.06230

Code (1)

dtak/power-constrained-bandits-public 공식 구현

Tasks

Decision Making Multi-Armed Bandits

Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits

2015-04-27 · NeurIPS 2015 12 · Huasen Wu, R. Srikant, Xin Liu, Chong Jiang

We study contextual bandits with budget and time constraints, referred to as constrained contextual bandits.The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they …

Multi-Armed Bandits

Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptions

2021-03-23 · Saeed Masoudian, Yevgeny Seldin

We derive improved regret bounds for the Tsallis-INF algorithm of Zimmert and Seldin (2021). We show that in adversarial regimes with a $(\Delta,C,T)$ self-bounding constraint the algorithm achieves $\mathcal{O}\left(\le…

Resourceful Contextual Bandits

2014-02-27 · Ashwinkumar Badanidiyuru, John Langford, Aleksandrs Slivkins

We study contextual bandits with ancillary constraints on resources, which are common in real-world applications such as choosing ads or dynamic pricing of items. We design the first algorithm for solving these problems …

Multi-Armed Bandits

Multi-Task Representation Learning for Conservative Linear Bandits

2026-05-12 · Jiabin Lin, Shana Moothedath arxiv

This paper presents the Constrained Multi-Task Representation Learning (CMTRL) framework for linear bandits. We consider T linear bandit tasks in a d dimensional space, which share a common low-dimensional representation…

Representation Learning

Thompson Sampling for Linearly Constrained Bandits

2020-04-20 · Vidit Saxena, Joseph E. Gonzalez, Joakim Jaldén

We address multi-armed bandits (MAB) where the objective is to maximize the cumulative reward under a probabilistic linear constraint. For a few real-world instances of this problem, constrained extensions of the well-kn…

Multi-Armed Bandits Thompson Sampling