Article

Free access

On the necessity of Occam algorithms

Authors:

L. PittAuthors Info & Claims

STOC '90: Proceedings of the twenty-second annual ACM symposium on Theory of Computing

Pages 54 - 63

https://doi.org/10.1145/100216.100223

Published: 01 April 1990 Publication History

First page of PDF

References

[1]

D. Angluin. Negative results for equivalence queries. Technical Report YALEU/DCS/RR-648, Department of Computer Science, Yale University, September 1988. To appear, Machine Learning. A preliminary version appears in the Proceedings of the 1989 Workshop on Computational Learning Theory.]]

[2]

A. Blumer, A. Ehrenfeucht, D. ttaussler, and M. Warmuth. Oecam's razor. Information Processing Letters, 24:377-380, 1987.]]

Digital Library

[3]

A. Blumer, A. Ehrenfeucht, D. Haussler, and M. Warmuth. Learnability and the Vapnik- Chervonenkis dimension. J. ACM, 36(4):929-965, October 1989.]]

Digital Library

[4]

A. Ehrenfeueht, D. Haussler, M. Kearns, and L. G. Valiant. A general lower bound on the number of examples needed for learning. Information and Computation, 82:247-261, 1989.]]

Digital Library

[5]

D. Haussler. Learning conjunctive concepts in structural domains. Machine Learning, 4(1):7-40, October 1989.]]

Digital Library

[6]

D. Haussler, M. Kearns, N. Littlestone, and M. K. Warmuth. Equivalence of models for polynomial learnability. In Proceedings of the 1988 Workshop on Computational Learning Theory, pages 42-55, San Mateo, CA, August 1988. Morgan Kaufmann. To appear in Information and Computation.]]

Digital Library

[7]

D. Haussler and L. Pitt, editors. Proceedings of the 1988 Workshop on Computational Learning Theory. Morgan Kaufmann, San Mateo, CA, 1988.]]

Digital Library

[8]

M. Kearns and L. G. Valiant. Cryptographic limitations on learning Boolean formulae and finite automata. In Proceedings of the 21st Annual ACM Symposium on Theory of Computing, pages 433- 444, New York, May 1989. ACM.]]

Digital Library

[9]

William of Occam. Quodlibeta Septem (in translation). Circa 1320.]]

[10]

L. Pitt and L. G. Valiant. Computational limitations on learning from examples. J. ACM, 35(4):965-984, 1988.]]

Digital Library

[11]

L. Pitt and M. K. Warmuth. The minimum consistent DFA problem cannot be approximated within any polynomial. Technical Report UIUCDCS-R-89-1499, University of Illinois at Urbana-Champaign, February 1989. To appear, J. ACM. A preliminary version appears in the 21st annual ACM Symposium on Theory of Computing, May 1989.]]

Digital Library

[12]

R. L. Rivest, D. Haussler, and M. K. Warmuth, editors. Proceedings of the 1989 Workshop on Computational Learning Theory. Morgan Kaufmann, San Mateo, CA, 1989.]]

Digital Library

[13]

R. Schapire. The strength of weak learnability. Technical Report MIT/LCS/TM-415, MIT Laboratory for Computer Science, October 1989. To appear, Machine Learning. A preliminary version appears in the Proceedings of the 30th Annual IEEE Symposium on Foundations of Computer Science, IEEE Computer Society Press, October, 1989.]]

Digital Library

[14]

R. Sloan. Computational learning theory: New models and algorithms. Technical Report MIT/LCS/TR-448, Ph.D. Thesis, MIT, 1989.]]

[15]

L. G. Valiant. A theory of the learnable. Communications of the ACM, 27(11):1134-1142, 1984.]]

Digital Library

[16]

M. K. Warmuth. Towards representation independence in PAC-learning. In Proceedings of AII-89 Workshop on Analogical and Inductive Inference; Lecture Notes in Artificial Intelligence 397, pages 78-103, Heidelberg, October 1989. Springer-Verlag.]]

Digital Library

Cited By

Sweke RSeifert JHangleiter DEisert J(2021)On the Quantum versus Classical Learnability of Discrete DistributionsQuantum10.22331/q-2021-03-23-4175(417)Online publication date: 23-Mar-2021
https://doi.org/10.22331/q-2021-03-23-417
Ishai YKushilevitz EOstrovsky RSahai A(2019)Cryptographic SensingAdvances in Cryptology – CRYPTO 201910.1007/978-3-030-26954-8_19(583-604)Online publication date: 1-Aug-2019
https://doi.org/10.1007/978-3-030-26954-8_19
Swarup S(2010)The Classification Game: Complexity Regularization through InteractionCoordination, Organizations, Institutions and Norms in Agent Systems V10.1007/978-3-642-14962-7_19(289-303)Online publication date: 2010
https://doi.org/10.1007/978-3-642-14962-7_19
Show More Cited By

Index Terms

On the necessity of Occam algorithms

Recommendations

Sharpening Occam's razor

We provide a new representation-independent formulation of Occam's razor theorem, based on Kolmogorov complexity. This new formulation allows us to: (i) obtain better sample complexity than both length-based [Blumer et al., Inform. Process. Lett. 24 (...
Occam's Razor
NIPS'00: Proceedings of the 13th International Conference on Neural Information Processing Systems

The Bayesian paradigm apparently only sometimes gives rise to Occam's Razor; at other times very large models perform well. We give simple examples of both kinds of behaviour. The two views are reconciled when measuring complexity of functions, rather ...
Causal Learning with Occam’s Razor
Abstract
Occam’s razor directs us to adopt the simplest hypothesis consistent with the evidence. Learning theory provides a precise definition of the inductive simplicity of a hypothesis for a given learning problem. This definition specifies a learning ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

STOC '90: Proceedings of the twenty-second annual ACM symposium on Theory of Computing

April 1990

574 pages

ISBN:0897913612

DOI:10.1145/100216

Editor:
Harriet Ortiz

Copyright © 1990 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGACT: ACM Special Interest Group on Algorithms and Computation Theory

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 April 1990

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Article

Conference

STOC90

Sponsor:

SIGACT

STOC90: 22nd Annual ACM Symposium on Theory of Computing

May 13 - 17, 1990

Maryland, Baltimore, USA

Acceptance Rates

Overall Acceptance Rate 1,469 of 4,586 submissions, 32%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

25
Total Citations
View Citations
557
Total Downloads

Downloads (Last 12 months)50
Downloads (Last 6 weeks)16

Reflects downloads up to 03 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Sweke RSeifert JHangleiter DEisert J(2021)On the Quantum versus Classical Learnability of Discrete DistributionsQuantum10.22331/q-2021-03-23-4175(417)Online publication date: 23-Mar-2021
https://doi.org/10.22331/q-2021-03-23-417
Ishai YKushilevitz EOstrovsky RSahai A(2019)Cryptographic SensingAdvances in Cryptology – CRYPTO 201910.1007/978-3-030-26954-8_19(583-604)Online publication date: 1-Aug-2019
https://doi.org/10.1007/978-3-030-26954-8_19
Swarup S(2010)The Classification Game: Complexity Regularization through InteractionCoordination, Organizations, Institutions and Norms in Agent Systems V10.1007/978-3-642-14962-7_19(289-303)Online publication date: 2010
https://doi.org/10.1007/978-3-642-14962-7_19
Swarup S(2009)The classification gameProceedings of the 5th international conference on Coordination, organizations, institutions, and norms in agent systems10.5555/1886594.1886616(289-303)Online publication date: 12-May-2009
https://dl.acm.org/doi/10.5555/1886594.1886616
Juba BCohen WMoore A(2006)Estimating relatedness via data compressionProceedings of the 23rd international conference on Machine learning10.1145/1143844.1143900(441-448)Online publication date: 25-Jun-2006
https://dl.acm.org/doi/10.1145/1143844.1143900
Denis FGilleron R(2005)PAC learning under helpful distributionsAlgorithmic Learning Theory10.1007/3-540-63577-7_40(132-145)Online publication date: 9-Jun-2005
https://doi.org/10.1007/3-540-63577-7_40
Hancock TJiang TLi MTromp J(2005)Lower bounds on learning decision lists and treesSTACS 9510.1007/3-540-59042-0_102(527-538)Online publication date: 1-Jun-2005
https://doi.org/10.1007/3-540-59042-0_102
Turán G(2005)A survey of some aspects of computational learning theoryFundamentals of Computation Theory10.1007/3-540-54458-5_53(89-103)Online publication date: 9-Jun-2005
https://doi.org/10.1007/3-540-54458-5_53
Pitt L(2005)Inductive inference, DFAs, and computational complexityAnalogical and Inductive Inference10.1007/3-540-51734-0_50(18-44)Online publication date: 26-May-2005
https://doi.org/10.1007/3-540-51734-0_50
Yu FLeung V(2002)Mobility-based predictive call admission control and bandwidth reservation in wireless cellular networksComputer Networks: The International Journal of Computer and Telecommunications Networking10.1016/S1389-1286(01)00269-938:5(577-589)Online publication date: 5-Apr-2002
https://dl.acm.org/doi/10.1016/S1389-1286%2801%2900269-9
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents