Functional Sequential Treatment Allocation with Covariates

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kock, Anders Bredahl, Preinerstorfer, David, Veliyev, Bezirgen
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909439502581760
author Kock, Anders Bredahl
Preinerstorfer, David
Veliyev, Bezirgen
author_facet Kock, Anders Bredahl
Preinerstorfer, David
Veliyev, Bezirgen
contents We consider a multi-armed bandit problem with covariates. Given a realization of the covariate vector, instead of targeting the treatment with highest conditional expectation, the decision maker targets the treatment which maximizes a general functional of the conditional potential outcome distribution, e.g., a conditional quantile, trimmed mean, or a socio-economic functional such as an inequality, welfare or poverty measure. We develop expected regret lower bounds for this problem, and construct a near minimax optimal assignment policy.
format Preprint
id arxiv_https___arxiv_org_abs_2001_10996
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Functional Sequential Treatment Allocation with Covariates
Kock, Anders Bredahl
Preinerstorfer, David
Veliyev, Bezirgen
Machine Learning
Econometrics
Statistics Theory
We consider a multi-armed bandit problem with covariates. Given a realization of the covariate vector, instead of targeting the treatment with highest conditional expectation, the decision maker targets the treatment which maximizes a general functional of the conditional potential outcome distribution, e.g., a conditional quantile, trimmed mean, or a socio-economic functional such as an inequality, welfare or poverty measure. We develop expected regret lower bounds for this problem, and construct a near minimax optimal assignment policy.
title Functional Sequential Treatment Allocation with Covariates
topic Machine Learning
Econometrics
Statistics Theory
url https://arxiv.org/abs/2001.10996