Article

Free access

Using and combining predictors that specialize

Authors:

Yoav Freund,

Robert E. Schapire,

Yoram Singer,

Manfred K. WarmuthAuthors Info & Claims

STOC '97: Proceedings of the twenty-ninth annual ACM symposium on Theory of computing

Pages 334 - 343

https://doi.org/10.1145/258533.258616

Published: 04 May 1997 Publication History

PDF eReader

References

[1]

Avrim Blum. Empirical support for winnow and weighted-majority based algorithms: results on a calendar scheduling domain. In m195, pages 64-72, 1995.

Google Scholar

[2]

Nicol6 Cesa-Bianchi, Yoav Freund, David P. Hehnbold, David Haussler, Robert E. Schhpire, and Manfred K. Warmuth. How to use expert advice. In Proceedings ql' the 13ven~-Fitth Annual ACM Symposium on the Theory of Computing, pages 382-391, 1993. To appear, Journal q f the Association.for Computing Machinery.

Digital Library

Google Scholar

[3]

William W. Cohen and Yoram Singer. Context-sensitive learning methods for text categorization. In sigir96, pages 307-315, 1996.

Digital Library

Google Scholar

[4]

Thomas M. Cover. Universal portfolios. Mathematical Finance, I(1):1-29, January 1991.

Crossref

Google Scholar

[5]

Thomas M. Cover and Aaron Shenhar. Compound Bayes predictors for sequences with apparent Markov structure. IEEE Transactions on Systems, Man, and Cybernetics, SMC-7(6):421-424, June 1977.

Google Scholar

[6]

Alfredo DeSantis, George Markowsky, and Mark N. Wegman. Learning probabilistic prediction functions. In Proceedings qt' the 1988 Worlc~hop on Computational Learning Theory, pages 312-328, 1988.

Digital Library

Google Scholar

[7]

Robert G. Gallager. lnJbrmation Theory and Reliable Communication. John Wiley & Sons, 1968.

Digital Library

Google Scholar

[8]

David Haussler, Jyrki Kivinen, and Manfred K. Warmuth. Tight worst-case loss bounds for predicting with expert advice. In Computational Learning Theory: Second European Con j'i~rence, Euro- COLT '95, pages 69-83. Springer-Verlag, 1995.

Digital Library

Google Scholar

[9]

David P. Helmbold, Jyrki Kivinen, and Manfred K. Warmuth. Worstcase loss bounds for sigmoided neurons. In Advances in Neural Inlbrnmtion Processing Syste~ 7, pages 309-315, 1995.

Google Scholar

[10]

David P. Helmbold and Robert E. Schapire. Predicting nearly as well as the best pruning of a decision tree. In Proceedings qf the Eighth Annual Con~'erence on Computational Learning Theory, pages 61-68, 1995.

Digital Library

Google Scholar

[11]

Mark Herbster and Manfred Warmuth. Tracking the best expert. In Proceedings of the TweO'~h International Conference on Machine Learning, pages 286-294, 1995.

Google Scholar

[12]

Jyrki Kivinen and Manfred K. Warmuth. Additive versus exponentiated gradient updates for linear prediction. In swc95, pages 209-218, 1995. See also technical report UCSC-CRL-94-16, University of California, Santa Cruz, Computer Research Laboratory.

Digital Library

Google Scholar

[13]

Nick Littlestone. Learning when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285-318, 1988.

Crossref

Google Scholar

[14]

Nick Littlestone and Manfred K. Warmuth. The weighted majority algorithm, lnt'brmation and Computation, 108:212-261, 1994.

Digital Library

Google Scholar

[15]

Neri Merhav, Meir Feder, and Michael Gutman. Some properties of sequential predictors for binary Markov sources. IEEE Transactions on ln/ormation Theory, 39(3):887-892, May 1993.

Crossref

Google Scholar

[16]

Jorma Rissanen and Glen G. Langdon, Jr. Universal modeling and coding. IEEE Transactions on ln{brmation Theory, 1T-27(!): 12-23, January 1981.

Google Scholar

[17]

Dana Ron, Yoram Singer, and Naftali Iishby. Learning probabilistic automata with variable memory length. In Proceedings o1" the Seventh Annual ACM Conlerence on Computational Learning Theory, pages 35-46, 1994.

Digital Library

Google Scholar

[18]

V.G. Vovk. A game of prediction with expert advice. In Proceedings of the Eighth Annual Conl'krence on Computational Learning Theory, 1995.

Digital Library

Google Scholar

[19]

Volodimir G. Vovk. Aggregating strategies. In Proceedings of the Third Annual Workxhop on Computational Learning Theory, pages 371-383, 1990.

Digital Library

Google Scholar

[20]

Marcelo J. Weinberger, Abraham Lempel, and Jacob Ziv. A sequential algorithm for the universal coding of finite-memory sources. IEEE Transactions on ln{ormation Theory, 38(3):1002-1014, May 1992.

Crossref

Google Scholar

[21]

Frans M. J. Willems, Yuri M. Shtarkov, and Tjalling J. Tjalkens. The context tree weighting method: basic properties. IEEE Transactions on Information Theory, 41(3):653-664, 1995.

Digital Library

Google Scholar

Cited By

View all

Bansak KLee SManshadi VNiazadeh RPaulson E(2024)Dynamic Matching with Post-Allocation Service and its Application to Refugee ResettlementSSRN Electronic Journal10.2139/ssrn.4748762Online publication date: 2024
https://doi.org/10.2139/ssrn.4748762
Shi RPalomar D(2024)SAOFTRL: A Novel Adaptive Algorithmic Framework for Enhancing Online Portfolio SelectionIEEE Transactions on Signal Processing10.1109/TSP.2024.349569672(5291-5305)Online publication date: 2024
https://doi.org/10.1109/TSP.2024.3495696
Litvinenko DBerikov V(2024)Building an Ensemble of Time Series Models Using Empirical Risk Space2024 International Russian Automation Conference (RusAutoCon)10.1109/RusAutoCon61949.2024.10694116(751-756)Online publication date: 8-Sep-2024
https://doi.org/10.1109/RusAutoCon61949.2024.10694116
Show More Cited By

Index Terms

Using and combining predictors that specialize

Recommendations

Multiple-block ahead branch predictors
ASPLOS VII: Proceedings of the seventh international conference on Architectural support for programming languages and operating systems

A basic rule in computer architecture is that a processor cannot execute an application faster than it fetches its instructions. This paper presents a novel cost-effective mechanism called the two-block ahead branch predictor. Information from the ...
Multiple-block ahead branch predictors

A basic rule in computer architecture is that a processor cannot execute an application faster than it fetches its instructions. This paper presents a novel cost-effective mechanism called the two-block ahead branch predictor. Information from the ...
Multiple-block ahead branch predictors

A basic rule in computer architecture is that a processor cannot execute an application faster than it fetches its instructions. This paper presents a novel cost-effective mechanism called the two-block ahead branch predictor. Information from the ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

STOC '97: Proceedings of the twenty-ninth annual ACM symposium on Theory of computing

May 1997

752 pages

ISBN:0897918886

DOI:10.1145/258533

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]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 04 May 1997

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Article

Conference

STOC97

Sponsor:

SIGACT

STOC97: 29th Annual Symposium on Theory of Computing

May 4 - 6, 1997

Texas, El Paso, USA

Acceptance Rates

STOC '97 Paper Acceptance Rate 75 of 211 submissions, 36%;

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

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

117
Total Citations
View Citations
1,462
Total Downloads

Downloads (Last 12 months)196
Downloads (Last 6 weeks)18

Reflects downloads up to 27 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Bansak KLee SManshadi VNiazadeh RPaulson E(2024)Dynamic Matching with Post-Allocation Service and its Application to Refugee ResettlementSSRN Electronic Journal10.2139/ssrn.4748762Online publication date: 2024
https://doi.org/10.2139/ssrn.4748762
Shi RPalomar D(2024)SAOFTRL: A Novel Adaptive Algorithmic Framework for Enhancing Online Portfolio SelectionIEEE Transactions on Signal Processing10.1109/TSP.2024.349569672(5291-5305)Online publication date: 2024
https://doi.org/10.1109/TSP.2024.3495696
Litvinenko DBerikov V(2024)Building an Ensemble of Time Series Models Using Empirical Risk Space2024 International Russian Automation Conference (RusAutoCon)10.1109/RusAutoCon61949.2024.10694116(751-756)Online publication date: 8-Sep-2024
https://doi.org/10.1109/RusAutoCon61949.2024.10694116
Antoniadis ACugliari JFasiolo MGoude YPoggi JAntoniadis ACugliari JFasiolo MGoude YPoggi J(2024)Aggregation of ExpertsStatistical Learning Tools for Electricity Load Forecasting10.1007/978-3-031-60339-6_6(113-130)Online publication date: 15-Aug-2024
https://doi.org/10.1007/978-3-031-60339-6_6
Pasteris SHicks CMavroudis VOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Nearest neighbour with bandit feedbackProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3667014(20320-20351)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3667014
Peng BRubinstein A(2023)Near Optimal Memory-Regret Tradeoff for Online Learning2023 IEEE 64th Annual Symposium on Foundations of Computer Science (FOCS)10.1109/FOCS57990.2023.00069(1171-1194)Online publication date: 6-Nov-2023
https://doi.org/10.1109/FOCS57990.2023.00069
Remlinger CAlasseur CBrière MMikael J(2023)Expert Aggregation for Financial ForecastingThe Journal of Finance and Data Science10.1016/j.jfds.2023.100108(100108)Online publication date: Nov-2023
https://doi.org/10.1016/j.jfds.2023.100108
Saleem SHejazi FOstovar N(2023)Health monitoring of ultra high fiber performance reinforced concrete communication tower using machine learning algorithmsJournal of Civil Structural Health Monitoring10.1007/s13349-023-00688-313:4-5(1105-1130)Online publication date: 24-Apr-2023
https://doi.org/10.1007/s13349-023-00688-3
Lee DNoarov GPai MRoth AKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Online minimax multiobjective optimizationProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3602376(29051-29063)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3602376
Zhang LJiang WYi JYang TKoyejo SMohamed SAgarwal ABelgrave DCho KOh A(2022)Smoothed online convex optimization based on discounted-normal-predictorProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3600626(4928-4942)Online publication date: 28-Nov-2022
https://dl.acm.org/doi/10.5555/3600270.3600626
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

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

Cited By

Index Terms

Recommendations

Multiple-block ahead branch predictors

Multiple-block ahead branch predictors

Multiple-block ahead branch predictors