Encyclopedia of Machine Learning and Data Mining

2017 Edition
| Editors: Claude Sammut, Geoffrey I. Webb

Active Learning Theory

  • Sanjoy Dasgupta
Reference work entry
DOI: https://doi.org/10.1007/978-1-4899-7687-1_7

Definition

The term active learning applies to a wide range of situations in which a learner is able to exert some control over its source of data. For instance, when fitting a regression function, the learner may itself supply a set of data points at which to measure response values, in the hope of reducing the variance of its estimate. Such problems have been studied for many decades under the rubric of experimental design (Chernoff 1972; Fedorov 1972). More recently, there has been substantial interest within the machine learning community in the specific task of actively learning binary classifiers. This task presents several fundamental statistical and algorithmic challenges, and an understanding of its mathematical underpinnings is only gradually emerging. This brief survey will describe some of the progress that has been made so far.

Learning from Labeled and Unlabeled Data

In the machine learning literature, the task of learning a classifier has traditionally been studied in...

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

Recommended Reading

  1. Angluin D (2001) Queries revisited. In: Proceedings of the 12th international conference on algorithmic learning theory, Washington, DC, pp 12–31zbMATHGoogle Scholar
  2. Balcan M-F, Beygelzimer A, Langford J (2006) Agnostic active learning. In: International conference on machine learning. ACM Press, New York, pp 65–72Google Scholar
  3. Balcan M-F, Broder A, Zhang T (2007) Margin based active learning. In: Conference on learning theory, San Diego, pp 35–50zbMATHGoogle Scholar
  4. Baum EB, Lang K (1992) Query learning can work poorly when a human oracle is used. In: International joint conference on neural networks, BaltimoreGoogle Scholar
  5. Beygelzimer A, Dasgupta S, Langford J (2009) Importance weighted active learning. In: International conference on machine learning. ACM Press, New York, pp 49–56Google Scholar
  6. Cesa-Bianchi N, Gentile C, Zaniboni L (2004) Worst-case analysis of selective sampling for linear-threshold algorithms. In: Advances in neural information processing systemszbMATHGoogle Scholar
  7. Chernoff H (1972) Sequential analysis and optimal design. CBMS-NSF regional conference series in applied mathematics, vol 8. SIAM, PhiladelphiaGoogle Scholar
  8. Cohn D, Atlas L, Ladner R (1994) Improving generalization with active learning. Mach Learn 15(2):201–221Google Scholar
  9. Dasgupta S (2005) Coarse sample complexity bounds for active learning. Advances in neural information processing systems. Morgan Kaufmann, San MateoGoogle Scholar
  10. Dasgupta S, Kalai A, Monteleoni C (2005) Analysis of perceptron-based active learning. In: 18th annual conference on learning theory, Bertinoro, pp 249–263Google Scholar
  11. Dasgupta S, Hsu DJ, Monteleoni C (2007) A general agnostic active learning algorithm. Advances in neural information processing systemsGoogle Scholar
  12. Fedorov VV (1972) Theory of optimal experiments (trans: Studden WJ, Klimko EM). Academic Press, New YorkGoogle Scholar
  13. Freund Y, Seung S, Shamir E, Tishby N (1997) Selective sampling using the query by committee algorithm. Mach Learn J 28:133–168zbMATHCrossRefGoogle Scholar
  14. Friedman E (2009) Active learning for smooth problems. In: Conference on learning theory, Montreal, pp 343–352Google Scholar
  15. Gilad-Bachrach R, Navot A, Tishby N (2005) Query by committeee made real. Advances in neural information processing systemsGoogle Scholar
  16. Hanneke S (2007a) Teaching dimension and the complexity of active learning. In: Conference on learning theory, San Diego, pp 66–81Google Scholar
  17. Hanneke S (2007b) A bound on the label complexity of agnostic active learning. In: International conference on machine learning, Corvallis, pp 353–360Google Scholar
  18. Haussler D (1992) Decision-theoretic generalizations of the PAC model for neural net and other learning applications. Inf Comput 100(1):78–150MathSciNetzbMATHCrossRefGoogle Scholar
  19. Seung HS, Opper M, Sompolinsky H (1992) Query by committee. In: Conference on computational learning theory, Victoria, pp 287–294Google Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  • Sanjoy Dasgupta
    • 1
  1. 1.University of CaliforniaLa JollaUSA