Research

Paper

TESTING March 09, 2026

Unifying On- and Off-Policy Variance Reduction Methods

Authors

Olivier Jeunen

Abstract

Continuous and efficient experimentation is key to the practical success of user-facing applications on the web, both through online A/B-tests and off-policy evaluation. Despite their shared objective -- estimating the incremental value of a treatment -- these domains often operate in isolation, utilising distinct terminologies and statistical toolkits. This paper bridges that divide by establishing a formal equivalence between their canonical variance reduction methods. We prove that the standard online Difference-in-Means estimator is mathematically identical to an off-policy Inverse Propensity Scoring estimator equipped with an optimal (variance-minimising) additive control variate. Extending this unification, we demonstrate that widespread regression adjustment methods (such as CUPED, CUPAC, and ML-RATE) are structurally equivalent to Doubly Robust estimation. This unified view extends our understanding of commonly used approaches, and can guide practitioners and researchers working on either class of problems.

Metadata

arXiv ID: 2603.08370
Provider: ARXIV
Primary Category: stat.ML
Published: 2026-03-09
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.08370v1</id>\n    <title>Unifying On- and Off-Policy Variance Reduction Methods</title>\n    <updated>2026-03-09T13:32:39Z</updated>\n    <link href='https://arxiv.org/abs/2603.08370v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.08370v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Continuous and efficient experimentation is key to the practical success of user-facing applications on the web, both through online A/B-tests and off-policy evaluation. Despite their shared objective -- estimating the incremental value of a treatment -- these domains often operate in isolation, utilising distinct terminologies and statistical toolkits. This paper bridges that divide by establishing a formal equivalence between their canonical variance reduction methods.\n  We prove that the standard online Difference-in-Means estimator is mathematically identical to an off-policy Inverse Propensity Scoring estimator equipped with an optimal (variance-minimising) additive control variate. Extending this unification, we demonstrate that widespread regression adjustment methods (such as CUPED, CUPAC, and ML-RATE) are structurally equivalent to Doubly Robust estimation. This unified view extends our understanding of commonly used approaches, and can guide practitioners and researchers working on either class of problems.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='stat.ML'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='stat.ME'/>\n    <published>2026-03-09T13:32:39Z</published>\n    <arxiv:primary_category term='stat.ML'/>\n    <author>\n      <name>Olivier Jeunen</name>\n    </author>\n  </entry>"
}