How Tight Are the Vapnik-Chervonenkis Bounds?

Author:

Cohn David1,Tesauro Gerald2

Affiliation:

1. Department of Computer Science and Engineering, University of Washington, Seattle, WA 98195 USA

2. IBM Watson Research Center, P.O. Box 704, Yorktown Heights, NY 10598 USA

Abstract

We describe a series of numerical experiments that measure the average generalization capability of neural networks trained on a variety of simple functions. These experiments are designed to test the relationship between average generalization performance and the worst-case bounds obtained from formal learning theory using the Vapnik-Chervonenkis (VC) dimension (Blumer et al. 1989; Haussler et al. 1990). Recent statistical learning theories (Tishby et al. 1989; Schwartz et al. 1990) suggest that surpassing these bounds might be possible if the spectrum of possible generalizations has a “gap” near perfect performance. We indeed find that, in some cases, the average generalization is significantly better than the VC bound: the approach to perfect performance is exponential in the number of examples m, rather than the 1/m result of the bound. However, in these cases, we have not found evidence of the gap predicted by the above statistical theories. In other cases, we do find the 1/m behavior of the VC bound, and in these cases, the numerical prefactor is closely related to the prefactor contained in the bound.

Publisher

MIT Press - Journals

Subject

Cognitive Neuroscience,Arts and Humanities (miscellaneous)

Cited by 44 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Resolution of similar patterns in a solvable model of unsupervised deep learning with structured data;Chaos, Solitons & Fractals;2024-05

2. Critical properties of the SAT/UNSAT transitions in the classification problem of structured data;Journal of Statistical Mechanics: Theory and Experiment;2021-11-01

3. A theory of universal learning;Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing;2021-06-15

4. Statistical learning theory of structured data;Physical Review E;2020-09-14

5. Beyond the Storage Capacity: Data-Driven Satisfiability Transition;Physical Review Letters;2020-09-14

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3