平摊变分推理:系统回顾

IF 4.5 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Journal of Artificial Intelligence Research Pub Date : 2023-10-15 DOI:10.1613/jair.1.14258
Ankush Ganguly, Sanjana Jain, Ukrit Watchareeruetai
{"title":"平摊变分推理:系统回顾","authors":"Ankush Ganguly, Sanjana Jain, Ukrit Watchareeruetai","doi":"10.1613/jair.1.14258","DOIUrl":null,"url":null,"abstract":"The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem. This property enables VI to be faster than several sampling-based techniques. However, the traditional VI algorithm is not scalable to large data sets and is unable to readily infer out-of-bounds data points without re-running the optimization process. Recent developments in the field, like stochastic-, black box-, and amortized-VI, have helped address these issues. Generative modeling tasks nowadays widely make use of amortized VI for its efficiency and scalability, as it utilizes a parameterized function to learn the approximate posterior density parameters. In this paper, we review the mathematical foundations of various VI techniques to form the basis for understanding amortized VI. Additionally, we provide an overview of the recent trends that address several issues of amortized VI, such as the amortization gap, generalization issues, inconsistent representation learning, and posterior collapse. Finally, we analyze alternate divergence measures that improve VI optimization.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"6 1","pages":"0"},"PeriodicalIF":4.5000,"publicationDate":"2023-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Amortized Variational Inference: A Systematic Review\",\"authors\":\"Ankush Ganguly, Sanjana Jain, Ukrit Watchareeruetai\",\"doi\":\"10.1613/jair.1.14258\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem. This property enables VI to be faster than several sampling-based techniques. However, the traditional VI algorithm is not scalable to large data sets and is unable to readily infer out-of-bounds data points without re-running the optimization process. Recent developments in the field, like stochastic-, black box-, and amortized-VI, have helped address these issues. Generative modeling tasks nowadays widely make use of amortized VI for its efficiency and scalability, as it utilizes a parameterized function to learn the approximate posterior density parameters. In this paper, we review the mathematical foundations of various VI techniques to form the basis for understanding amortized VI. Additionally, we provide an overview of the recent trends that address several issues of amortized VI, such as the amortization gap, generalization issues, inconsistent representation learning, and posterior collapse. Finally, we analyze alternate divergence measures that improve VI optimization.\",\"PeriodicalId\":54877,\"journal\":{\"name\":\"Journal of Artificial Intelligence Research\",\"volume\":\"6 1\",\"pages\":\"0\"},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2023-10-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Artificial Intelligence Research\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1613/jair.1.14258\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Artificial Intelligence Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1613/jair.1.14258","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 3

摘要

变分推理(VI)的核心原理是将计算复杂后验概率密度的统计推理问题转化为可处理的优化问题。这个属性使VI比一些基于采样的技术更快。然而,传统的VI算法无法扩展到大型数据集,并且在不重新运行优化过程的情况下无法轻松推断出越界数据点。该领域的最新发展,如随机-、黑盒-和平摊- vi,有助于解决这些问题。由于平摊VI算法利用参数化函数来学习近似后验密度参数,因此由于其效率和可扩展性,生成建模任务广泛使用平摊VI算法。在本文中,我们回顾了各种VI技术的数学基础,以形成理解平摊VI的基础。此外,我们概述了解决平摊VI的几个问题的最新趋势,如平摊差距、泛化问题、不一致表示学习和后向崩溃。最后,我们分析了改进VI优化的备选发散措施。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Amortized Variational Inference: A Systematic Review
The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem. This property enables VI to be faster than several sampling-based techniques. However, the traditional VI algorithm is not scalable to large data sets and is unable to readily infer out-of-bounds data points without re-running the optimization process. Recent developments in the field, like stochastic-, black box-, and amortized-VI, have helped address these issues. Generative modeling tasks nowadays widely make use of amortized VI for its efficiency and scalability, as it utilizes a parameterized function to learn the approximate posterior density parameters. In this paper, we review the mathematical foundations of various VI techniques to form the basis for understanding amortized VI. Additionally, we provide an overview of the recent trends that address several issues of amortized VI, such as the amortization gap, generalization issues, inconsistent representation learning, and posterior collapse. Finally, we analyze alternate divergence measures that improve VI optimization.
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
Journal of Artificial Intelligence Research
Journal of Artificial Intelligence Research 工程技术-计算机:人工智能
CiteScore
9.60
自引率
4.00%
发文量
98
审稿时长
4 months
期刊介绍: JAIR(ISSN 1076 - 9757) covers all areas of artificial intelligence (AI), publishing refereed research articles, survey articles, and technical notes. Established in 1993 as one of the first electronic scientific journals, JAIR is indexed by INSPEC, Science Citation Index, and MathSciNet. JAIR reviews papers within approximately three months of submission and publishes accepted articles on the internet immediately upon receiving the final versions. JAIR articles are published for free distribution on the internet by the AI Access Foundation, and for purchase in bound volumes by AAAI Press.
期刊最新文献
Collective Belief Revision Competitive Equilibria with a Constant Number of Chores Improving Resource Allocations by Sharing in Pairs A General Model for Aggregating Annotations Across Simple, Complex, and Multi-Object Annotation Tasks Asymptotics of K-Fold Cross Validation
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1