自豪与概率

IF 1.4 2区哲学 Q1 HISTORY & PHILOSOPHY OF SCIENCE

Philosophy of Science Pub Date : 2024-01-26 DOI:10.1017/psa.2023.177

Francesca Zaffora Blando

{"title":"自豪与概率","authors":"Francesca Zaffora Blando","doi":"10.1017/psa.2023.177","DOIUrl":null,"url":null,"abstract":"Abstract\n Bayesian agents, argues Belot (2013), are orgulous: they believe in inductive success even when guaranteed to fail on a topologically typical collection of data streams. Here we shed light on how pervasive this phenomenon is. We identify several classes of inductive problems for which Bayesian convergence to the truth is topologically typical. However, we also show that, for all sufficiently complex classes, there are inductive problems for which convergence is topologically atypical. Lastly, we identify specific topologically typical collections of data streams, observing which guarantees convergence to the truth across all problems from certain natural classes of effective inductive problems.","PeriodicalId":54620,"journal":{"name":"Philosophy of Science","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2024-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Pride and Probability\",\"authors\":\"Francesca Zaffora Blando\",\"doi\":\"10.1017/psa.2023.177\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract\\n Bayesian agents, argues Belot (2013), are orgulous: they believe in inductive success even when guaranteed to fail on a topologically typical collection of data streams. Here we shed light on how pervasive this phenomenon is. We identify several classes of inductive problems for which Bayesian convergence to the truth is topologically typical. However, we also show that, for all sufficiently complex classes, there are inductive problems for which convergence is topologically atypical. Lastly, we identify specific topologically typical collections of data streams, observing which guarantees convergence to the truth across all problems from certain natural classes of effective inductive problems.\",\"PeriodicalId\":54620,\"journal\":{\"name\":\"Philosophy of Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2024-01-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Philosophy of Science\",\"FirstCategoryId\":\"98\",\"ListUrlMain\":\"https://doi.org/10.1017/psa.2023.177\",\"RegionNum\":2,\"RegionCategory\":\"哲学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"HISTORY & PHILOSOPHY OF SCIENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Philosophy of Science","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1017/psa.2023.177","RegionNum":2,"RegionCategory":"哲学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"HISTORY & PHILOSOPHY OF SCIENCE","Score":null,"Total":0}

引用次数: 0

摘要

摘要贝洛特（Belot，2013 年）认为，贝叶斯代理是orgulous：它们相信归纳成功，即使在拓扑上典型的数据流集合上保证会失败。在此，我们将揭示这一现象的普遍性。我们确定了几类归纳问题，对于这些问题，贝叶斯法收敛到真相在拓扑上是典型的。然而，我们也证明，对于所有足够复杂的类别，也有一些归纳问题的收敛在拓扑上是非典型的。最后，我们确定了特定的拓扑典型数据流集合，通过观察这些数据流集合，可以保证从某些自然类的有效归纳问题中的所有问题都能收敛到真相。

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

Pride and Probability

Abstract Bayesian agents, argues Belot (2013), are orgulous: they believe in inductive success even when guaranteed to fail on a topologically typical collection of data streams. Here we shed light on how pervasive this phenomenon is. We identify several classes of inductive problems for which Bayesian convergence to the truth is topologically typical. However, we also show that, for all sufficiently complex classes, there are inductive problems for which convergence is topologically atypical. Lastly, we identify specific topologically typical collections of data streams, observing which guarantees convergence to the truth across all problems from certain natural classes of effective inductive problems.

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

Philosophy of Science 管理科学-科学史与科学哲学

CiteScore

3.10

自引率

5.90%

发文量

128

审稿时长

6-12 weeks

期刊介绍： Since its inception in 1934, Philosophy of Science, along with its sponsoring society, the Philosophy of Science Association, has been dedicated to the furthering of studies and free discussion from diverse standpoints in the philosophy of science. The journal contains essays, discussion articles, and book reviews.