神经熵

Akhil Premkumar
{"title":"神经熵","authors":"Akhil Premkumar","doi":"arxiv-2409.03817","DOIUrl":null,"url":null,"abstract":"We examine the connection between deep learning and information theory\nthrough the paradigm of diffusion models. Using well-established principles\nfrom non-equilibrium thermodynamics we can characterize the amount of\ninformation required to reverse a diffusive process. Neural networks store this\ninformation and operate in a manner reminiscent of Maxwell's demon during the\ngenerative stage. We illustrate this cycle using a novel diffusion scheme we\ncall the entropy matching model, wherein the information conveyed to the\nnetwork during training exactly corresponds to the entropy that must be negated\nduring reversal. We demonstrate that this entropy can be used to analyze the\nencoding efficiency and storage capacity of the network. This conceptual\npicture blends elements of stochastic optimal control, thermodynamics,\ninformation theory, and optimal transport, and raises the prospect of applying\ndiffusion models as a test bench to understand neural networks.","PeriodicalId":501082,"journal":{"name":"arXiv - MATH - Information Theory","volume":"56 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Neural Entropy\",\"authors\":\"Akhil Premkumar\",\"doi\":\"arxiv-2409.03817\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We examine the connection between deep learning and information theory\\nthrough the paradigm of diffusion models. Using well-established principles\\nfrom non-equilibrium thermodynamics we can characterize the amount of\\ninformation required to reverse a diffusive process. Neural networks store this\\ninformation and operate in a manner reminiscent of Maxwell's demon during the\\ngenerative stage. We illustrate this cycle using a novel diffusion scheme we\\ncall the entropy matching model, wherein the information conveyed to the\\nnetwork during training exactly corresponds to the entropy that must be negated\\nduring reversal. We demonstrate that this entropy can be used to analyze the\\nencoding efficiency and storage capacity of the network. This conceptual\\npicture blends elements of stochastic optimal control, thermodynamics,\\ninformation theory, and optimal transport, and raises the prospect of applying\\ndiffusion models as a test bench to understand neural networks.\",\"PeriodicalId\":501082,\"journal\":{\"name\":\"arXiv - MATH - Information Theory\",\"volume\":\"56 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - MATH - Information Theory\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.03817\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - MATH - Information Theory","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.03817","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

我们通过扩散模型的范例来研究深度学习与信息论之间的联系。利用非平衡热力学的既定原理,我们可以描述逆转扩散过程所需的信息量。神经网络会存储这些信息,并在生成阶段以类似麦克斯韦恶魔的方式运行。我们使用一种我们称之为熵匹配模型的新型扩散方案来说明这种循环,其中训练过程中传递给网络的信息正好对应于逆转过程中必须否定的熵。我们证明,这种熵可以用来分析网络的编码效率和存储容量。这一概念图景融合了随机最优控制、热力学、信息论和最优传输等元素,为应用扩散模型作为理解神经网络的试验台提供了前景。
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
Neural Entropy
We examine the connection between deep learning and information theory through the paradigm of diffusion models. Using well-established principles from non-equilibrium thermodynamics we can characterize the amount of information required to reverse a diffusive process. Neural networks store this information and operate in a manner reminiscent of Maxwell's demon during the generative stage. We illustrate this cycle using a novel diffusion scheme we call the entropy matching model, wherein the information conveyed to the network during training exactly corresponds to the entropy that must be negated during reversal. We demonstrate that this entropy can be used to analyze the encoding efficiency and storage capacity of the network. This conceptual picture blends elements of stochastic optimal control, thermodynamics, information theory, and optimal transport, and raises the prospect of applying diffusion models as a test bench to understand neural networks.
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
自引率
0.00%
发文量
0
期刊最新文献
Fluid Antenna-enabled Integrated Sensing, Communication, and Computing Systems On the second-order zero differential properties of several classes of power functions over finite fields Synchronizable hybrid subsystem codes Decoding Algorithm Correcting Single-Insertion Plus Single-Deletion for Non-binary Quantum Codes A Symbol-Pair Decoder for CSS Codes
×
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