Abstract
We generalize on-line learning to handle delays in receiving labels for instances. After receiving an instance x, the algorithm may need to make predictions on several new instances before the label for x is returned by the environment. We give two simple techniques for converting a traditional on-line algorithm into an algorithm for solving a delayed on-line problem. One technique is for instances generated by an adversary; the other is for instances generated by a distribution. We show how these techniques effect the original on-line mistake bounds by giving upper-bounds and restricted lower-bounds on the number of mistakes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Littlestone, N.: Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning 2, 285–318 (1988)
Androutsopoulos, I., Koutsias, J., Chandrinos, K., Paliouras, G., Spyropoulos, C.: An evaluation of naive bayesian anti-spam filtering (2000)
Padmanabhan, V.N., Mogul, J.C.: Using predictive prefetching to improve world wide web latency. ACM SIGCOMM Computer Communication Review 26, 22–36 (1996)
Littlestone, N.: Redundant noisy attributes, attribute errors, and linear-threshold learning using winnow. In: Proceedings of the Third Annual Conference on Computational Learning Theory, pp. 147–156 (1991)
Helmbold, D.P., Long, P.M.: Tracking drifting concepts using random examples. In: Proceedings of the Third Annual Conference on Computational Learning Theory, pp. 13–23 (1991)
Kuh, A., Petsche, T., Rivest, R.L.: Learning time-varying concepts. In: Neural Information Processing Systems Three, pp. 183–189. Morgan Kaufmann Publishers, Inc., San Francisco (1991)
Auer, P., Warmuth, M.K.: Tracking the best disjunction. In: Proceedings of the 36th annual symposium on foundations of computer science, pp. 312–321. IEEE Computer Society Press, Los Alamitos (1995)
Devroye, L., Györfi, L., Lugosi, G.: A Probabilistic Theory of Pattern Recognition. Springer, New York (1991)
Littlestone, N.: Comparing several linear-threshold learning algorithms on tasks involving superfluous attributes. In: Proceeding of the Twelve International Conference on Machine Learning, pp. 353–361 (1995)
Littlestone, N., Mesterharm, C.: An apobayesian relative of winnow. In: Neural Information Processing Systems Nine, pp. 204–210. MIT Press, Cambridge (1997)
Minsky, M.L., Papert, S.A.: Perceptrons. MIT Press, Cambridge (1969)
Li, Y., Long, P.: The relaxed online maximum margin algorithm. In: Neural Information Processing Systems Twelve, pp. 498–504. MIT Press, Cambridge (2000)
Mesterharm, C.: Tracking linear-threshold concepts with winnow. Journal of Machine Learning Research 4, 819–838 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mesterharm, C. (2005). On-line Learning with Delayed Label Feedback. In: Jain, S., Simon, H.U., Tomita, E. (eds) Algorithmic Learning Theory. ALT 2005. Lecture Notes in Computer Science(), vol 3734. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11564089_31
Download citation
DOI: https://doi.org/10.1007/11564089_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29242-5
Online ISBN: 978-3-540-31696-1
eBook Packages: Computer ScienceComputer Science (R0)