基于亚高斯和可微重要性加权的极大极小非策略评价与学习

IF 4.6 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Alberto Maria Metelli, Alessio Russo, Marcello Restelli
{"title":"基于亚高斯和可微重要性加权的极大极小非策略评价与学习","authors":"Alberto Maria Metelli,&nbsp;Alessio Russo,&nbsp;Marcello Restelli","doi":"10.1016/j.artint.2025.104419","DOIUrl":null,"url":null,"abstract":"<div><div>In this work, we study the statistical properties of the <em>off-policy estimation</em> problem, i.e., estimating expectations under a target policy using samples collected from a different policy. We begin by presenting a novel minimax concentration lower bound that highlights the fundamental limits of off-policy estimation. We then analyze two well-known <em>importance weighting</em> (IW) techniques: vanilla IW and self-normalized importance weighting (SN). For both methods, we derive concentration and anti-concentration results, showing that their concentration rates are provably suboptimal compared to our lower bound. Observing that this undesired behavior arises from the <em>heavy-tailed</em> nature of the IW and SN estimators, we propose a new class of parametric estimators based on a transformation using the <em>power mean</em> (PM), which is no longer heavy-tailed. We study the theoretical properties of the PM estimator in terms of bias and variance. We show that, with suitable (possibly data-driven) tuning of its parameters, the PM estimator satisfies two key properties under certain conditions: (<em>i</em>) it achieves a <em>subgaussian</em> concentration rate that matches our lower bound and (<em>ii</em>) it maintains differentiability with respect to the target policy. Finally, we validate our approach through numerical simulations on both synthetic datasets and contextual bandits, comparing it against standard off-policy evaluation and learning baselines.<span><span><sup>1</sup></span></span></div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104419"},"PeriodicalIF":4.6000,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Minimax off-policy evaluation and learning with subgaussian and differentiable importance weighting\",\"authors\":\"Alberto Maria Metelli,&nbsp;Alessio Russo,&nbsp;Marcello Restelli\",\"doi\":\"10.1016/j.artint.2025.104419\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>In this work, we study the statistical properties of the <em>off-policy estimation</em> problem, i.e., estimating expectations under a target policy using samples collected from a different policy. We begin by presenting a novel minimax concentration lower bound that highlights the fundamental limits of off-policy estimation. We then analyze two well-known <em>importance weighting</em> (IW) techniques: vanilla IW and self-normalized importance weighting (SN). For both methods, we derive concentration and anti-concentration results, showing that their concentration rates are provably suboptimal compared to our lower bound. Observing that this undesired behavior arises from the <em>heavy-tailed</em> nature of the IW and SN estimators, we propose a new class of parametric estimators based on a transformation using the <em>power mean</em> (PM), which is no longer heavy-tailed. We study the theoretical properties of the PM estimator in terms of bias and variance. We show that, with suitable (possibly data-driven) tuning of its parameters, the PM estimator satisfies two key properties under certain conditions: (<em>i</em>) it achieves a <em>subgaussian</em> concentration rate that matches our lower bound and (<em>ii</em>) it maintains differentiability with respect to the target policy. Finally, we validate our approach through numerical simulations on both synthetic datasets and contextual bandits, comparing it against standard off-policy evaluation and learning baselines.<span><span><sup>1</sup></span></span></div></div>\",\"PeriodicalId\":8434,\"journal\":{\"name\":\"Artificial Intelligence\",\"volume\":\"348 \",\"pages\":\"Article 104419\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2025-09-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Artificial Intelligence\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0004370225001389\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0004370225001389","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

在这项工作中,我们研究了非策略估计问题的统计性质,即使用从不同策略收集的样本估计目标策略下的期望。我们首先提出了一个新的极大极小浓度下界,突出了非政策估计的基本限制。然后,我们分析了两种众所周知的重要性加权(IW)技术:香草重要性加权和自标准化重要性加权(SN)。对于这两种方法,我们都得到了浓缩和反浓缩的结果,表明与我们的下界相比,它们的浓缩率可证明是次优的。观察到这种不希望的行为是由IW和SN估计器的重尾性质引起的,我们提出了一类新的基于使用功率均值(PM)变换的参数估计器,它不再是重尾。我们从偏置和方差的角度研究了PM估计量的理论性质。我们表明,通过适当的(可能是数据驱动的)参数调整,PM估计器在某些条件下满足两个关键性质:(i)它实现了与我们的下界匹配的亚高斯浓度率;(ii)它保持了相对于目标策略的可微性。最后,我们通过在合成数据集和上下文强盗上的数值模拟来验证我们的方法,并将其与标准的非政策评估和学习基线进行比较
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Minimax off-policy evaluation and learning with subgaussian and differentiable importance weighting
In this work, we study the statistical properties of the off-policy estimation problem, i.e., estimating expectations under a target policy using samples collected from a different policy. We begin by presenting a novel minimax concentration lower bound that highlights the fundamental limits of off-policy estimation. We then analyze two well-known importance weighting (IW) techniques: vanilla IW and self-normalized importance weighting (SN). For both methods, we derive concentration and anti-concentration results, showing that their concentration rates are provably suboptimal compared to our lower bound. Observing that this undesired behavior arises from the heavy-tailed nature of the IW and SN estimators, we propose a new class of parametric estimators based on a transformation using the power mean (PM), which is no longer heavy-tailed. We study the theoretical properties of the PM estimator in terms of bias and variance. We show that, with suitable (possibly data-driven) tuning of its parameters, the PM estimator satisfies two key properties under certain conditions: (i) it achieves a subgaussian concentration rate that matches our lower bound and (ii) it maintains differentiability with respect to the target policy. Finally, we validate our approach through numerical simulations on both synthetic datasets and contextual bandits, comparing it against standard off-policy evaluation and learning baselines.1
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Artificial Intelligence
Artificial Intelligence 工程技术-计算机:人工智能
CiteScore
11.20
自引率
1.40%
发文量
118
审稿时长
8 months
期刊介绍: The Journal of Artificial Intelligence (AIJ) welcomes papers covering a broad spectrum of AI topics, including cognition, automated reasoning, computer vision, machine learning, and more. Papers should demonstrate advancements in AI and propose innovative approaches to AI problems. Additionally, the journal accepts papers describing AI applications, focusing on how new methods enhance performance rather than reiterating conventional approaches. In addition to regular papers, AIJ also accepts Research Notes, Research Field Reviews, Position Papers, Book Reviews, and summary papers on AI challenges and competitions.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信