Computational learning theory
This article needs additional citations for verification. (November 2018) (Learn how and when to remove this template message) |
Machine learning and data mining |
---|
Machine-learning venues |
In computer science, computational learning theory (or just learning theory) is a subfield of artificial intelligence devoted to studying the design and analysis of machine learning algorithms.[1]
Contents
Overview[edit]
Theoretical results in machine learning mainly deal with a type of inductive learning called supervised learning. In supervised learning, an algorithm is given samples that are labeled in some useful way. For example, the samples might be descriptions of mushrooms, and the labels could be whether or not the mushrooms are edible. The algorithm takes these previously labeled samples and uses them to induce a classifier. This classifier is a function that assigns labels to samples, including samples that have not been seen previously by the algorithm. The goal of the supervised learning algorithm is to optimise some measure of performance such as minimising the number of mistakes made on new samples.
In addition to performance bounds, computational learning theory studies the time complexity and feasibility of learning.[citation needed] In computational learning theory, a computation is considered feasible if it can be done in polynomial time.[citation needed] There are two kinds of time complexity results:
- Positive results – Showing that a certain class of functions is learnable in polynomial time.
- Negative results – Showing that certain classes cannot be learned in polynomial time.
Negative results often rely on commonly believed, but yet unproven assumptions,[citation needed] such as:
- Computational complexity – P ≠ NP (the P versus NP problem);
- Cryptographic – One-way functions exist.
There are several different approaches to computational learning theory. These differences are based on making assumptions about the inference principles used to generalize from limited data.[citation needed] This includes different definitions of probability (see frequency probability, Bayesian probability) and different assumptions on the generation of samples.[citation needed] The different approaches include:[citation needed]
- Exact learning, proposed by Dana Angluin;
- Probably approximately correct learning (PAC learning), proposed by Leslie Valiant;
- VC theory, proposed by Vladimir Vapnik and Alexey Chervonenkis;
- Bayesian inference;
- Algorithmic learning theory, from the work of E. Mark Gold;
- Online machine learning, from the work of Nick Littlestone.
Computational learning theory has led to several practical algorithms.[according to whom?] For example, PAC theory inspired boosting, VC theory led to support vector machines, and Bayesian inference led to belief networks (by Judea Pearl).
See also[edit]
References[edit]
Surveys[edit]
- Angluin, D. 1992. Computational learning theory: Survey and selected bibliography. In Proceedings of the Twenty-Fourth Annual ACM Symposium on Theory of Computing (May 1992), pages 351–369. http://portal.acm.org/citation.cfm?id=129712.129746
- D. Haussler. Probably approximately correct learning. In AAAI-90 Proceedings of the Eight National Conference on Artificial Intelligence, Boston, MA, pages 1101–1108. American Association for Artificial Intelligence, 1990. http://citeseer.ist.psu.edu/haussler90probably.html
VC dimension[edit]
- V. Vapnik and A. Chervonenkis. On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications, 16(2):264–280, 1971.
Feature selection[edit]
- A. Dhagat and L. Hellerstein, "PAC learning with irrelevant attributes", in 'Proceedings of the IEEE Symp. on Foundation of Computer Science', 1994. http://citeseer.ist.psu.edu/dhagat94pac.html
Inductive inference[edit]
- Gold, E. Mark (1967). "Language identification in the limit" (PDF). Information and Control. 10 (5): 447–474. doi:10.1016/S0019-9958(67)91165-5.
Optimal O notation learning[edit]
- Oded Goldreich, Dana Ron. On universal learning algorithms. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.47.2224
Negative results[edit]
- M. Kearns and Leslie Valiant. 1989. Cryptographic limitations on learning boolean formulae and finite automata. In Proceedings of the 21st Annual ACM Symposium on Theory of Computing, pages 433–444, New York. ACM. http://citeseer.ist.psu.edu/kearns89cryptographic.html
Boosting (machine learning)[edit]
- Robert E. Schapire. The strength of weak learnability. Machine Learning, 5(2):197–227, 1990 http://citeseer.ist.psu.edu/schapire90strength.html
Occam Learning[edit]
- Blumer, A.; Ehrenfeucht, A.; Haussler, D.; Warmuth, M. K. "Occam's razor" Inf.Proc.Lett. 24, 377–380, 1987.
- A. Blumer, A. Ehrenfeucht, D. Haussler, and M. K. Warmuth. Learnability and the Vapnik-Chervonenkis dimension. Journal of the ACM, 36(4):929–865, 1989.
Probably approximately correct learning[edit]
- L. Valiant. A Theory of the Learnable. Communications of the ACM, 27(11):1134–1142, 1984.
Error tolerance[edit]
- Michael Kearns and Ming Li. Learning in the presence of malicious errors. SIAM Journal on Computing, 22(4):807–837, August 1993. http://citeseer.ist.psu.edu/kearns93learning.html
- Kearns, M. (1993). Efficient noise-tolerant learning from statistical queries. In Proceedings of the Twenty-Fifth Annual ACM Symposium on Theory of Computing, pages 392–401. http://citeseer.ist.psu.edu/kearns93efficient.html
Equivalence[edit]
- D.Haussler, M.Kearns, N.Littlestone and M. Warmuth, Equivalence of models for polynomial learnability, Proc. 1st ACM Workshop on Computational Learning Theory, (1988) 42-55.
- Pitt, L.; Warmuth, M. K. (1990). "Prediction-Preserving Reducibility" (PDF). Journal of Computer and System Sciences. 41 (3): 430–467. doi:10.1016/0022-0000(90)90028-J.
A description of some of these publications is given at important publications in machine learning.