Skip to main content
SpringerLink
Log in

Sequential Sampling Techniques for Algorithmic Learning Theory

  • Conference paper
  • First Online:
Algorithmic Learning Theory (ALT 2000)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1968))

Included in the following conference series:

Abstract

A sequential sampling algorithm or adaptive sampling algorithm is a sampling algorithm that obtains instances sequentially one by one and determines from these instances whether it has already seen enough number of instances for achieving a given task. In this paper, we present two typical sequential sampling algorithms. By using simple estimation problems for our example, we explain when and how to use such sampling algorithms for designing adaptive learning algorithms.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. J. Balcazár, a personal communication. 28

    Google Scholar 

  2. H. Cherno., A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations, Annals of Mathematical Statistics 23, pp.493–509, 1952. 29

    Article  MathSciNet  Google Scholar 

  3. C. Dominogo, Faster near-optimal reinforcement learning: adding adaptiveness to the E3 algorithm, in Proc. f 10th Algorithmic Learning Theory Conference (ALT’99), Lecture Notes in Artificial Intelligence 1720, Springer-Verlag, pp.241–251, 1999. 28, 32

    Google Scholar 

  4. C. Domingo and O. Watanabe, Scaling up a boosting-based learner via adaptive sampling, in Proc. f Knowledge Discovery and Data Mining (PAKDD’00), Lecture Notes in Artificial Intelligence 1805, Springer-Verlag, pp.317–328, 2000. 28

    Google Scholar 

  5. C. Domingo and O. Watanabe, MadaBoost: a modification of AdaBoost, in Proc. f 13th Annual Conference on Computational Learning Theory (COLT’00), Morgan Kaufmann, pp.180–189, 2000. 28

    Google Scholar 

  6. C. Domingo, R. Gavaldá, and O. Watanabe, Practical algorithms for on-line selection, in Proc. f the First Intl. onference on Discovery Science, Lecture Notes in Artificial Intelligence 1532, Springer-Verlag, pp.150–161, 1998. 27, 38

    Google Scholar 

  7. C. Domingo, R. Gavaldá, and O. Watanabe, Adaptive sampling methods for scaling up knowledge discovery algorithms, in Proc. f the Second Intl. onference on Discovery Science, Lecture Notes in Artificial Intelligence, Springer-Verlag, pp.-, 1999. 27, 38

    Google Scholar 

  8. C. Domingo, R. Gavaldá, and O. Watanabe, Adaptive sampling methods for scaling up knowledge discovery algorithms, J. nowledge Discovery and Data Mining, to appear. (Also available as a research report C-136, Dept. f Math. and Computing Sciences, Tokyo Institute of Technology, from http://www.is.titech.ac.jp/research/research-report/C/) 27, 37, 38

  9. W. Feller, An Introduction to Probability Theory and its Applications (Third Edition), John Wiley & Sons, 1968. 27, 30

    Google Scholar 

  10. B. K. Ghosh and P. K. Sen eds., Handbook of Sequential Analysis, Marcel Dekker, 1991. 28

    Google Scholar 

  11. B. K. Ghosh, M. Mukhopadhyay, P. K. Sen, Sequential Estimation, Wiley, 1997. 28

    Google Scholar 

  12. R. Greiner, PALO: a probabilistic hill-climbing algorithm, Artificial Intelligence, 84, pp.177–204, 1996. 28

    Article  MathSciNet  Google Scholar 

  13. W. Hoeffding, Probability inequalities for sums of bounded random variables, Journal of the American Statistical Association 58, pp.13–30, 1963. 29

    Article  MATH  MathSciNet  Google Scholar 

  14. M. Kearns and S. Singh, Near-optimal reinforcement learning in polynomial time, in Proc. f the 16th Intl. onference on Machine Learning (ICML’98), Morgan Kaufmann, 260–268, 1998. 32

    Google Scholar 

  15. R. J. Lipton, J. F. Naughton, D. A. Schneider, and S. Seshadri, Effcient sampling strategies for relational database operations, Theoretical Computer Science 116, pp.195–226, 1993. 28, 33

    Article  MATH  MathSciNet  Google Scholar 

  16. R. J. Lipton and J. F. Naughton, Query size estimation by adaptive sampling, Journal of Computer and System Science 51, pp.18–25, 1995. 28, 33

    Article  MATH  MathSciNet  Google Scholar 

  17. J. F. Lynch, Analysis and application of adaptive sampling, in Proc. f the 19th ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems (PODS’99), ACM Press, pp.260–267, 1999. 28, 33

    Google Scholar 

  18. O. Maron and A. Moore, Hoeffding races: accelerating model selection search for classiffcation and function approximation, in Advances in Neural Information Processing Systems, Morgan Kaufmann, 59–66, 1994. 28

    Google Scholar 

  19. T. Scheffer and S. Wrobel, A sequential sampling algorithm for a general class of utility criteria, in Proc. f the 6th ACM SIGKDD Intl. Conference on Knowledge Discovery and Data Mining, ACM Press, 2000, to appear. 28, 37

    Google Scholar 

  20. P. Haas and A. Swami, Sequential sampling, procedures for query size estimation, IBM Research Report, RJ9101 (80915), 1992. 28

    Google Scholar 

  21. A. Wald, Sequential Analysis, John Wiley & Sons, 1947. 28

    Google Scholar 

  22. O. Watanabe, Simple sampling techniques for discovery science, IEICE Trans. Info. & Systems, E83-D (1), 19–26, 2000. (A preliminary version is available as a research report C-137, Dept. f Math. and Computing Sciences, Tokyo Institute of Technology, from http://www.is.titech.ac.jp/research/research-report/C/) 28, 30, 37

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dept. of Mathematical and Computing Sciences, Tokyo Institute of Technology, 152-8552, Tokyo, Japan

    Osamu Watanabe

Authors
  1. Osamu Watanabe
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Informatics, Kyushu University, Hakozaki 6-10-1, 812-8581, Fukuoka, Japan

    Hiroki Arimura

  2. School of Computing, National University of Singapore, 3 Science Drive 2, 117543, Singapore, Singapore

    Sanjay Jain

  3. School of Computer Science and Engineering, The University of New South Wales, 2052, Sydney, Australia

    Arun Sharma

Rights and permissions

Reprints and permissions

Copyright information

© 2001 Springer-Verlag Berlin Heidelberg 2001

About this paper

Cite this paper

Watanabe, O. (2001). Sequential Sampling Techniques for Algorithmic Learning Theory. In: Arimura, H., Jain, S., Sharma, A. (eds) Algorithmic Learning Theory. ALT 2000. Lecture Notes in Computer Science(), vol 1968. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-40992-0_3

Download citation

  • DOI: https://doi.org/10.1007/3-540-40992-0_3

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-41237-3

  • Online ISBN: 978-3-540-40992-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation