最优学习的悖论:一个信息缺口的视角

Y. Ben-Haim, S. Cogan
{"title":"最优学习的悖论:一个信息缺口的视角","authors":"Y. Ben-Haim, S. Cogan","doi":"10.1115/1.4062511","DOIUrl":null,"url":null,"abstract":"\n Engineering design and technological risk assessment both entail learning or discovering new knowledge. Optimal learning is a procedure whereby new knowledge is obtained while minimizing some specific measure of effort (e.g., time or money expended). A paradox is a statement that appears self-contradictory, contrary to common sense, or simply wrong, and yet might be true. The paradox of optimal learning is the assertion that a learning procedure cannot be optimized a priori—when designing the procedure—if the procedure depends on knowledge that the learning itself is intended to obtain. This is called a reflexive learning procedure. Many learning procedures can be optimized a priori. However, a priori optimization of a reflexive learning procedure is (usually) not possible. Most (but not all) reflexive learning procedures cannot be optimized without repeatedly implementing the procedure which may be very expensive. We discuss the prevalence of reflexive learning and present examples of the paradox. We also characterize those situations in which a reflexive learning procedure can be optimized. We discuss a response to the paradox (when it holds) based on the concept of robustness to uncertainty as developed in info-gap decision theory. We explain that maximizing the robustness is complementary to—but distinct from—minimizing a measure of effort of the learning procedure.","PeriodicalId":44694,"journal":{"name":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","volume":"69 1","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Paradox of Optimal Learning: An Info-Gap Perspective\",\"authors\":\"Y. Ben-Haim, S. Cogan\",\"doi\":\"10.1115/1.4062511\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n Engineering design and technological risk assessment both entail learning or discovering new knowledge. Optimal learning is a procedure whereby new knowledge is obtained while minimizing some specific measure of effort (e.g., time or money expended). A paradox is a statement that appears self-contradictory, contrary to common sense, or simply wrong, and yet might be true. The paradox of optimal learning is the assertion that a learning procedure cannot be optimized a priori—when designing the procedure—if the procedure depends on knowledge that the learning itself is intended to obtain. This is called a reflexive learning procedure. Many learning procedures can be optimized a priori. However, a priori optimization of a reflexive learning procedure is (usually) not possible. Most (but not all) reflexive learning procedures cannot be optimized without repeatedly implementing the procedure which may be very expensive. We discuss the prevalence of reflexive learning and present examples of the paradox. We also characterize those situations in which a reflexive learning procedure can be optimized. We discuss a response to the paradox (when it holds) based on the concept of robustness to uncertainty as developed in info-gap decision theory. We explain that maximizing the robustness is complementary to—but distinct from—minimizing a measure of effort of the learning procedure.\",\"PeriodicalId\":44694,\"journal\":{\"name\":\"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering\",\"volume\":\"69 1\",\"pages\":\"\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2023-06-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1115/1.4062511\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems Part B-Mechanical Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1115/1.4062511","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

工程设计和技术风险评估都需要学习或发现新的知识。最佳学习是一种获得新知识的过程,同时最小化某些特定的努力(例如,时间或金钱的花费)。悖论是一种看似自相矛盾的陈述,与常识相反,或者完全错误,但可能是真的。最优学习的悖论是,如果学习过程依赖于学习本身想要获得的知识,那么在设计过程时,就不能优先优化学习过程。这被称为反射性学习过程。许多学习过程可以先验地优化。然而,对反身性学习过程的先验优化(通常)是不可能的。大多数(但不是全部)反射性学习过程如果不反复执行可能非常昂贵的过程,就无法优化。我们讨论了反身性学习的普遍性,并提出了悖论的例子。我们还描述了那些可以优化反射学习过程的情况。我们根据信息差距决策理论中对不确定性的鲁棒性概念,讨论对悖论(当它成立时)的响应。我们解释说,最大化鲁棒性是互补的,但不同于最小化学习过程的努力措施。
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
Paradox of Optimal Learning: An Info-Gap Perspective
Engineering design and technological risk assessment both entail learning or discovering new knowledge. Optimal learning is a procedure whereby new knowledge is obtained while minimizing some specific measure of effort (e.g., time or money expended). A paradox is a statement that appears self-contradictory, contrary to common sense, or simply wrong, and yet might be true. The paradox of optimal learning is the assertion that a learning procedure cannot be optimized a priori—when designing the procedure—if the procedure depends on knowledge that the learning itself is intended to obtain. This is called a reflexive learning procedure. Many learning procedures can be optimized a priori. However, a priori optimization of a reflexive learning procedure is (usually) not possible. Most (but not all) reflexive learning procedures cannot be optimized without repeatedly implementing the procedure which may be very expensive. We discuss the prevalence of reflexive learning and present examples of the paradox. We also characterize those situations in which a reflexive learning procedure can be optimized. We discuss a response to the paradox (when it holds) based on the concept of robustness to uncertainty as developed in info-gap decision theory. We explain that maximizing the robustness is complementary to—but distinct from—minimizing a measure of effort of the learning procedure.
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
CiteScore
5.20
自引率
13.60%
发文量
34
期刊最新文献
Verification and Validation of Rotating Machinery Using Digital Twin Risk Approach Based On the Fram Model for Vessel Traffic Management A Fault Detection Framework Based On Data-driven Digital Shadows Domain Adaptation Of Population-Based Of Bolted Joint Structures For Loss Detection Of Tightening Torque Human-Comfort Evaluation for A Patient-Transfer Robot through A Human-Robot Mechanical Model
×
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