变分推理中近似误差的评价

IF 0.7 4区数学 Q3 STATISTICS & PROBABILITY

Statistics & Probability Letters Pub Date : 2025-07-25 DOI:10.1016/j.spl.2025.110505

Silvelyn Zwanzig , Rauf Ahmad

{"title":"变分推理中近似误差的评价","authors":"Silvelyn Zwanzig , Rauf Ahmad","doi":"10.1016/j.spl.2025.110505","DOIUrl":null,"url":null,"abstract":"<div><div>We show that in a linear model setting, the minimization problem in variational inference pertains to approximation error under suitable prior. We further show that the choice of prior preferred by the approximating member in mean-field family trades itself off with model assumptions. To demonstrate this, we also prove a result of general interest for linear algebra.</div></div>","PeriodicalId":49475,"journal":{"name":"Statistics & Probability Letters","volume":"226 ","pages":"Article 110505"},"PeriodicalIF":0.7000,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An appraisal of approximation error in variational inference\",\"authors\":\"Silvelyn Zwanzig , Rauf Ahmad\",\"doi\":\"10.1016/j.spl.2025.110505\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>We show that in a linear model setting, the minimization problem in variational inference pertains to approximation error under suitable prior. We further show that the choice of prior preferred by the approximating member in mean-field family trades itself off with model assumptions. To demonstrate this, we also prove a result of general interest for linear algebra.</div></div>\",\"PeriodicalId\":49475,\"journal\":{\"name\":\"Statistics & Probability Letters\",\"volume\":\"226 \",\"pages\":\"Article 110505\"},\"PeriodicalIF\":0.7000,\"publicationDate\":\"2025-07-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Statistics & Probability Letters\",\"FirstCategoryId\":\"100\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0167715225001506\",\"RegionNum\":4,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"STATISTICS & PROBABILITY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Statistics & Probability Letters","FirstCategoryId":"100","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167715225001506","RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"STATISTICS & PROBABILITY","Score":null,"Total":0}

引用次数: 0

摘要

我们证明了在线性模型设置下，变分推理中的最小化问题属于在适当先验条件下的近似误差问题。我们进一步表明，平均场族中近似成员的先验优选选择与模型假设相交换。为了证明这一点，我们还证明了线性代数中一个普遍感兴趣的结果。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

An appraisal of approximation error in variational inference

We show that in a linear model setting, the minimization problem in variational inference pertains to approximation error under suitable prior. We further show that the choice of prior preferred by the approximating member in mean-field family trades itself off with model assumptions. To demonstrate this, we also prove a result of general interest for linear algebra.

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

Statistics & Probability Letters 数学-统计学与概率论

CiteScore

1.60

自引率

0.00%

发文量

173

审稿时长

6 months

期刊介绍： Statistics & Probability Letters adopts a novel and highly innovative approach to the publication of research findings in statistics and probability. It features concise articles, rapid publication and broad coverage of the statistics and probability literature. Statistics & Probability Letters is a refereed journal. Articles will be limited to six journal pages (13 double-space typed pages) including references and figures. Apart from the six-page limitation, originality, quality and clarity will be the criteria for choosing the material to be published in Statistics & Probability Letters. Every attempt will be made to provide the first review of a submitted manuscript within three months of submission. The proliferation of literature and long publication delays have made it difficult for researchers and practitioners to keep up with new developments outside of, or even within, their specialization. The aim of Statistics & Probability Letters is to help to alleviate this problem. Concise communications (letters) allow readers to quickly and easily digest large amounts of material and to stay up-to-date with developments in all areas of statistics and probability. The mainstream of Letters will focus on new statistical methods, theoretical results, and innovative applications of statistics and probability to other scientific disciplines. Key results and central ideas must be presented in a clear and concise manner. These results may be part of a larger study that the author will submit at a later time as a full length paper to SPL or to another journal. Theory and methodology may be published with proofs omitted, or only sketched, but only if sufficient support material is provided so that the findings can be verified. Empirical and computational results that are of significant value will be published.