Article

Free access

Randomized approximate aggregating strategies and their applications to prediction and discrimination

Author:

Kenji YamanishiAuthors Info & Claims

COLT '95: Proceedings of the eighth annual conference on Computational learning theory

Pages 83 - 90

https://doi.org/10.1145/225298.225308

Published: 05 July 1995 Publication History

PDF eReader

References

[1]

Chan~ K.S.(1993)4 Asymptotic behavior of the Gibbs sampler. Jr~ American Statist. Assoc, 88~ 421:320-326o

Google Scholar

[2]

Clarke, B. and Barron, A.(1990). Information-theoretic asymptotics of Bayes methods, IEEE Trans~ Inform. Theory, IT-36,453-471o

Google Scholar

[3]

Dawid, A.(1984). Statistical theory: the presequential approach. J. R. Stat. S,c. A, 278-292.

Google Scholar

[4]

Gelfand~ A.E. and Smith, A.F.M.(1990). Samplingbased approach to calculating marginal densities. J.Am. Statist. Assoc., 85:398-409.

Crossref

Google Scholar

[5]

Geman, S. and Geman, D.(1984) Stochastic relaxation, Gibbs distributions, and the Bayes restoration of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-6, 721-741.

Digital Library

Google Scholar

[6]

Hastings, W.K.(1970). Monte Carlo sampling method using Markov chains and their applications. Biometrika, 57: 97-109.

Crossref

Google Scholar

[7]

Kivinen, J. and Warmuth, M.(1993). Using experts for predicting continuous outcomes. In Computational Learning Theory: EuroCOLT'9S, (pp.109-120), Oxford.

Digital Library

Google Scholar

[8]

Metropolis, N., Rosenbluth, M.N., Rosenbluth, A.H., Teller, A.H., Teller, E.(1953). Equations of state calculations by fast computation machines. J. Chemical Physics, 21:1087-1091.

Crossref

Google Scholar

[9]

Rissanen, J.(1989). Stochastic Complexity in Statistical fnqmry, World Scientific~

Digital Library

Google Scholar

[10]

Robert,G.O. and Polson N.G.(1994). On the geometric convergence of the Gibbs sampler~ J.R.Statist. S,c. B~ 56, 2:377-384.

Google Scholar

[11]

Rosenthal, J.(1993)o Minorization conditions and convergence rates for Markov chain Monte Carlo. Technical report No.9321~ Univ. of Toronto, Dept. of Statistics.

Google Scholar

[12]

Rosenthal, J.(1994). Analysis of the Gibbs sampler for a model related to James-Stein estimators. Technical report No.9413, Univ. of Toronto, Dept. of Statistics.

Google Scholar

[13]

Tanner, M.A. and Wong, I-I.Wo(1987)~ The calculation of posterior distributions by data augmentation. Jr. American Statist. Assoc., 82, 528-550.

Crossref

Google Scholar

[14]

Tierney, L.(1991). Exploring posterior distributions using Markov chains. In Proc. of 23rd Symp~ on the Interface, (pp.563-570).

Google Scholar

[15]

Vovk, V.G.(1990). Aggregating Strategies. Proceedings of the Third Annual Workshop on Computational Learning Theory, (pp.371-386), Morgan Kaufmann.

Digital Library

Google Scholar

[16]

Vovk, V.G.(1995). A game of prediction with expert advice. In Proc. COLT'95.

Digital Library

Google Scholar

[17]

Yamanishi, K.(1991). A loss bound model for on-line stochastic prediction strategies. In Proc. of COLT'91~ (pp. 290-302), Morgan Kaufmann.

Digital Library

Google Scholar

[18]

Yamanishi, K.(1995). Probably almost discriminative learning. Machine Learning, 18:23-50, Kluwer Academic Publishers.

Digital Library

Google Scholar

[19]

Yamanishi, K.(1994). Generalized stochastic complexity and its applications to learning. Proc. of CISSgJ, pp.763-768.

Google Scholar

[20]

Ziv, J.(1988). On classification with empirically observed statistics and universal data compression. IEEE Trans. IT, IT-34:278-286.

Crossref

Google Scholar

Cited By

View all

Vyugin MV'yugin V(2005)Predictive complexity and informationJournal of Computer and System Sciences10.1016/j.jcss.2004.10.00570:4(539-554)Online publication date: 1-Jun-2005
https://dl.acm.org/doi/10.1016/j.jcss.2004.10.005
Vyugin MV'yugin V(2002)On complexity of easy predictable sequencesInformation and Computation10.1016/S0890-5401(02)93164-0178:1(241-252)Online publication date: 10-Oct-2002
https://dl.acm.org/doi/10.1016/S0890-5401%2802%2993164-0
V'yugin V(2002)Does snooping help?Theoretical Computer Science10.1016/S0304-3975(01)00122-0276:1-2(407-415)Online publication date: 1-Apr-2002
https://dl.acm.org/doi/10.1016/S0304-3975%2801%2900122-0
Show More Cited By

Index Terms

Randomized approximate aggregating strategies and their applications to prediction and discrimination

Recommendations

Randomized Approximate Nearest Neighbor Search with Limited Adaptivity
Special Issue on SPAA 2016

We study the complexity of parallel data structures for approximate nearest neighbor search in d-dimensional Hamming space {0,1}^d. A classic model for static data structures is the cell-probe model [27]. We consider a cell-probe model with limited ...
Randomized Approximate Nearest Neighbor Search with Limited Adaptivity
SPAA '16: Proceedings of the 28th ACM Symposium on Parallelism in Algorithms and Architectures

We study the problem of approximate nearest neighbor search in $d$-dimensional Hamming space {0,1}^d. We study the complexity of the problem in the famous cell-probe model, a classic model for data structures. We consider algorithms in the cell-probe ...
Super-linear time-space tradeoff lower bounds for randomized computation
FOCS '00: Proceedings of the 41st Annual Symposium on Foundations of Computer Science

We prove the first time-space lower bound tradeoffs for randomized computation of decision problems. The bounds hold even in the case that the computation is allowed to have arbitrary probability of error on a small fraction of inputs. Our techniques ...

Comments

Information & Contributors

Information

Published In

COLT '95: Proceedings of the eighth annual conference on Computational learning theory

July 1995

464 pages

ISBN:0897917235

DOI:10.1145/225298

Chairman:
Wolfgang Maass
Technische Univ. Graz, Graz, Austria

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: 05 July 1995

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Article

Conference

8COLT95

Sponsor:

SIGAI
University of California
SIGACT

8COLT95: 8th Annual Conference on Computational Learning Theory

July 5 - 8, 1995

California, Santa Cruz, USA

Acceptance Rates

Overall Acceptance Rate 35 of 71 submissions, 49%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
224
Total Downloads

Downloads (Last 12 months)32
Downloads (Last 6 weeks)5

Reflects downloads up to 06 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Vyugin MV'yugin V(2005)Predictive complexity and informationJournal of Computer and System Sciences10.1016/j.jcss.2004.10.00570:4(539-554)Online publication date: 1-Jun-2005
https://dl.acm.org/doi/10.1016/j.jcss.2004.10.005
Vyugin MV'yugin V(2002)On complexity of easy predictable sequencesInformation and Computation10.1016/S0890-5401(02)93164-0178:1(241-252)Online publication date: 10-Oct-2002
https://dl.acm.org/doi/10.1016/S0890-5401%2802%2993164-0
V'yugin V(2002)Does snooping help?Theoretical Computer Science10.1016/S0304-3975(01)00122-0276:1-2(407-415)Online publication date: 1-Apr-2002
https://dl.acm.org/doi/10.1016/S0304-3975%2801%2900122-0
Vyugin MV’yugin V(2002)Predictive Complexity and InformationComputational Learning Theory10.1007/3-540-45435-7_7(90-105)Online publication date: 25-Jun-2002
https://doi.org/10.1007/3-540-45435-7_7
Vyugin MV'yugin V(2002)On Complexity of Easy Predictable SequencesInformation and Computation10.1006/inco.2002.3164178:1(241-252)Online publication date: Oct-2002
https://doi.org/10.1006/inco.2002.3164
Vyugin MV'yugin V(2001)Non-linear Inequalities between Predictive and Kolmogorov ComplexitiesAlgorithmic Learning Theory10.1007/3-540-45583-3_16(190-204)Online publication date: 31-Oct-2001
https://doi.org/10.1007/3-540-45583-3_16
Vovk V(1999)Derandomizing Stochastic Prediction StrategiesMachine Language10.1023/A:100759503238235:3(247-282)Online publication date: 1-Jun-1999
https://dl.acm.org/doi/10.1023/A%3A1007595032382
Vovk V(1998)A Game of Prediction with Expert AdviceJournal of Computer and System Sciences10.1006/jcss.1997.155656:2(153-173)Online publication date: 1-Apr-1998
https://dl.acm.org/doi/10.1006/jcss.1997.1556
Mukouchi TMatsushima THirasawa S(1997)Machine learning by a subset of hypotheses1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation10.1109/ICSMC.1997.635315(2533-2538)Online publication date: 1997
https://doi.org/10.1109/ICSMC.1997.635315
Yamanishi KBlum AKearns M(1996)A randomized approximation of the MDL for stochastic models with hidden variablesProceedings of the ninth annual conference on Computational learning theory10.1145/238061.238074(99-109)Online publication date: 1-Jan-1996
https://dl.acm.org/doi/10.1145/238061.238074
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Get Access

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

Randomized Approximate Nearest Neighbor Search with Limited Adaptivity

Randomized Approximate Nearest Neighbor Search with Limited Adaptivity

Super-linear time-space tradeoff lower bounds for randomized computation

Comments

Published In

Sponsors

Publisher

Publication History

Permissions

Check for updates

Qualifiers

Conference

Acceptance Rates

Other Metrics

Article Metrics

Other Metrics

Cited By

PDF

eReader

Login options

Full Access

References

Cited By

Index Terms

Recommendations

Randomized Approximate Nearest Neighbor Search with Limited Adaptivity

Randomized Approximate Nearest Neighbor Search with Limited Adaptivity

Super-linear time-space tradeoff lower bounds for randomized computation

Comments

Information

Published In

Sponsors

Publisher

Publication History

Permissions

Check for updates

Qualifiers

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

PDF

eReader

Get Access

Login options

Full Access

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations