Abstract
This paper examines learning problems in which the target function is allowed to change. The learner sees a sequence of random examples, labelled according to a sequence of functions, and must provide an accurate estimate of the target function sequence. We consider a variety of restrictions on how the target function is allowed to change, including infrequent but arbitrary changes, sequences that correspond to slow walks on a graph whose nodes are functions, and changes that are small on average, as measured by the probability of disagreements between consecutive functions. We first study estimation, in which the learner sees a batch of examples and is then required to give an accurate estimate of the function sequence. Our results provide bounds on the sample complexity and allowable drift rate for these problems. We also study prediction, in which the learner must produce online a hypothesis after each labelled example and the average misclassification probability over this hypothesis sequence should be small. Using a deterministic analysis in a general metric space setting, we provide a technique for constructing a successful prediction algorithm, given a successful estimation algorithm. This leads to sample complexity and drift rate bounds for the prediction of changing concepts.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Anthony, M. & Bartlett, P. L. (1999). Neural Network Learning: Theoretical Foundations. Cambridge, UK: Cambridge University Press.
Bartlett, P. L. (1992). Learning with a slowly changing distribution. In Proceedings of the 1992 Workshop on Computational Learning Theory (pp. 243–252).
Bartlett, P. L. & Helmbold, D. P. (1996). Learning changing problems. Technical report, Australian National University.
Barve, R. D. & Long, P. M. (1997). On the complexity of learning from drifting distributions. Information and Computation, 138(2), 101–123.
Bertoni, A., Campadelli, P., Morpurgo, A., & Panizza, S. (1992). Polynomial uniform convergence and polynomial sample learnability. In Proceedings of the 1992 Workshop on Computational Learning Theory (pp. 265–271).
Blum, A. & Chalasani, P. (1992). Learning switching concepts. In Proceeding of the fifth Annual Workshop on Computer Learning Theory (pp. 231–242). New York, NY: ACM Press.
Blumer, A., Ehrenfeucht, A., Haussler, D., & Warmuth, M. K. (1989). Learnability and the Vapnik-Chervonenkis Dimension. J. ACM, 36(4), 929–965.
Connolly, A. J., Chicharo, J. F., & Wilbers, P. (1992). Temperature modelling and prediction of steel strip in a HSM. In Control 92 Conference Proceedings. Institute of Engineers Australia.
Freund, Y. & Mansour, Y. (1997). Learning under persistent drift. In S. Ben-David, (Ed.), Computational Learning Theory: Third European Conference, Euro-COLT'97 (pp. 109–118). Springer.
Hagerup, T. & Rub, C. (1990). A guided tour of Chernov bounds. Inform. Proc. Lett., 33, 305–308.
Haussler, D. (1992). Decision theoretic generalizations of the PAC model for neural net and other learning applications. Inform. Comput., 100(1), 78–150.
Helmbold, D. P. & Long, P.M. (1994).Tracking drifting concepts by minimizing disagreements. Machine Learning, 14, 27.
Long, P. M. (1998). The complexity of learning according to two models of a drifting environment. In Proceedings of the Eleventh Annual Conference on Computational Learning Theory (pp. 116–125). ACM.
Merhav, N. & Feder, M. (1993). Universal schemes for sequential decision from individual data sequences. IEEE Transactions on Information Theory, 39(4), 1280–1292.
Vapnik, V. N. (1982). Estimation of Dependences Based on Empirical Data. New York: Springer-Verlag.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Bartlett, P.L., Ben-David, S. & Kulkarni, S.R. Learning Changing Concepts by Exploiting the Structure of Change. Machine Learning 41, 153–174 (2000). https://doi.org/10.1023/A:1007604202679
Issue Date:
DOI: https://doi.org/10.1023/A:1007604202679