Machine Learning

, Volume 69, Issue 2–3, pp 213–228

Active sampling for multiple output identification

Article
  • 200 Downloads

Abstract

We study functions with multiple output values, and use active sampling to identify an example for each of the possible output values. Our results for this setting include: (1) Efficient active sampling algorithms for simple geometric concepts, such as intervals on a line and axis parallel boxes. (2) A characterization for the case of binary output value in a transductive setting. (3) An analysis of active sampling with uniform distribution in the plane. (4) An efficient algorithm for the Boolean hypercube when each output value is a monomial.

Keywords

Active learning Active sampling Hitting VC dimension Transductive learning Output identification Separation dimension 

References

  1. Dasgupta, S. (2004). Analysis of a greedy active learning strategy. In Advances in neural information processing systems (NIPS). Google Scholar
  2. Dasgupta, S. (2005). Coarse sample complexity bounds for active learning. In Advances in neural information processing systems (NIPS). Google Scholar
  3. Dasgupta, S., Kalai, A., & Monteleoni, C. (2005). Analysis of perceptron-based active learning. In Eighteenth annual conference on learning theory (COLT). Google Scholar
  4. Edelstein, O., Farchi, E., Nir, Y., Ratzaby, G., & Ur, S. (2002). Multithreaded java program test generation. IBM Systems Journal, 41(3), 111–125. CrossRefGoogle Scholar
  5. Efron, B. (1965). The convex hull of a random set of points. Biometrika, 52, 331–343. MATHMathSciNetGoogle Scholar
  6. Feller, W. (1966). An introduction to probability theory and its applications (Vol. I). New York: Wiley. MATHGoogle Scholar
  7. Fine, S., & Ziv, A. (2003). Coverage directed test generation for functional verification using Bayesian networks. In Proceedings of the 40th design automation conference (pp. 286–291), June 2003. Google Scholar
  8. Fine, S., Gilad-Bachrach, R., & Shamir, E. (2002). Query by committee, linear separation and random walks. Theoretical Computer Science, 284(1). (A preliminary version appeared in EuroColt 1999). Google Scholar
  9. Freund, Y., Seung, H., Shamir, E., & Tishby, N. (1997). Selective sampling using the query by committee algorithm. Machine Learning, 28(2/3), 133–168. MATHCrossRefGoogle Scholar
  10. Gilad-Bachrach, R. (2006). Personal communication. Google Scholar
  11. Kulkarni, S. R., Mitter, S. K., & Tsitsiklis, J. N. (1993). Active learning using arbitrary binary valued queries. Machine Learning, 11, 23–35. MATHCrossRefGoogle Scholar
  12. Liere, R., & Tadepalli, P. (1997). Active learning with committees for text categorization. In AAAI-97. Google Scholar
  13. Linial, N., Luby, M., Saks, M., & Zuckerman, D. (1997). Efficient construction of a small hitting set for combinatorial rectangles in high dimension. Combinatorica, 17(2), 215–234. (A preliminary version appeared in STOC 1993.) MATHCrossRefMathSciNetGoogle Scholar
  14. Piziali, A. (2004). Functional verification coverage measurement and analysis. Berlin: Springer. Google Scholar
  15. Preparata, F. P., & Shamos, M.I. (1985). Computational geometry: an introduction. Berlin: Springer. Google Scholar
  16. Rényi, A., & Sulamke, R. (1963). Uber die konvexe hulle von n zufallig gewahlten punkten. Zeitschrift für Wahrscheinlichkeitstheorie, 2, 75–84. MATHCrossRefGoogle Scholar
  17. Sauer, N. (1972). On the density of family of sets. Journal of Combinatorial Theory, Series A, 13, 145–147. MATHCrossRefMathSciNetGoogle Scholar
  18. Seung, H. S., Opper, M., & Sompolinsky, H. (1992). Query by committee. In Proceedings of the fifth workshop on computational learning theory (pp. 287–294). San Mateo: Kaufman. CrossRefGoogle Scholar
  19. Srebro, N. (2006). Personal communication. Google Scholar
  20. Ur, S., & Yadin, Y. (1999). Micro-architecture coverage directed generation of test programs. In Proceedings of the 36th design automation conference (pp. 175–180), June 1999. Google Scholar
  21. Vapnik, V. N., & Chervonenkis, A. Y. (1971). On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications, XVI(2), 264–280. CrossRefMathSciNetGoogle Scholar
  22. Wile, B., Goss, J. C., & Roesner, W. (2005). Comprehensive functional verification the complete industry cycle. Amsterdam: Elsevier. Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.IBM Research Laboratory in HaifaMount Carmel, HaifaIsrael
  2. 2.School of Computer ScienceTel Aviv UniversityTel AvivIsrael

Personalised recommendations