Learnability and the Vapnik-Chervonenkis dimension
TL;DR: This paper shows that the essential condition for distribution-free learnability is finiteness of the Vapnik-Chervonenkis dimension, a simple combinatorial parameter of the class of concepts to be learned.
Abstract: Valiant's learnability model is extended to learning classes of concepts defined by regions in Euclidean space En. The methods in this paper lead to a unified treatment of some of Valiant's results, along with previous results on distribution-free convergence of certain pattern recognition algorithms. It is shown that the essential condition for distribution-free learnability is finiteness of the Vapnik-Chervonenkis dimension, a simple combinatorial parameter of the class of concepts to be learned. Using this parameter, the complexity and closure properties of learnable classes are analyzed, and the necessary and sufficient conditions are provided for feasible learnability.
Citations
More filters
TL;DR: An approximation algorithm for the hitting set problem when the VC-dimension of the set system is small is presented, which uses a linear programming relaxation to compute a probability measure for which @?-nets are always hitting sets.
141 citations
Cites background from "Learnability and the Vapnik-Chervon..."
...Theorem 6 ([1, 4]) Let F = (X,R) denote a set system with weights w(u)....
[...]
Posted Content•
TL;DR: A formal analysis of contentions of Schaffer (1993) proves that his contentions are valid, although some of his experiments must be interpreted with caution.
Abstract: In supervising learning it is commonly believed that penalizing complex functions help one avoid ``overfitting'' functions to data, and therefore improves generalization. It is also commonly believed that cross-validation is an effective way to choose amongst algorithms for fitting functions to data. In a recent paper, Schaffer (1993) presents experimental evidence disputing these claims. The current paper consists of a formal analysis of these contentions of Schaffer's. It proves that his contentions are valid, although some of his experiments must be interpreted with caution.
140 citations
Proceedings Article•
29 Jul 1990TL;DR: This paper surveys some recent theoretical results on the efficiency of machine learning algorithms and defines the notion of Probably Approximately Correct (PAC) learning, introduced by Valiant, and considers some criticisms of this model.
Abstract: This paper surveys some recent theoretical results on the efficiency of machine learning algorithms. The main tool described is the notion of Probably Approximately Correct (PAC) learning, introduced by Valiant. We define this learning model and then look at some of the results obtained in it. We then consider some criticisms of the PAC model and the extensions proposed to address these criticisms. Finally, we look briefly at other models recently proposed in computational learning theory.
139 citations
30 Oct 1989
TL;DR: The set cover algorithm is applied to learning theory, providing an NC algorithm for learning the concept class obtained by taking the closure under finite union or finite intersection of any concept class of finite VC dimension which has an NC hypothesis finder.
Abstract: NC approximation algorithms are given for the unweighted and weighted set cover problems. The algorithms use a linear number of processors and give a cover that has at most log n times the optimal size/weight, thus matching the performance of the best sequential algorithms. The set cover algorithm is applied to learning theory, providing an NC algorithm for learning the concept class obtained by taking the closure under finite union or finite intersection of any concept class of finite VC dimension which has an NC hypothesis finder. In addition, a linear-processor NC algorithm is given for a variant of the set cover problem and used to obtain NC algorithms for several problems in computational geometry. >
139 citations
IBM1
TL;DR: A new approach to classification rules or decision trees from examples by finding each feature's "obligation" to the class discrimination in the context of other features, which is a powerful alternative to the traditional methods.
Abstract: Deriving classification rules or decision trees from examples is an important problem. When there are too many features, discarding weak features before the derivation process is highly desirable. When there are numeric features, they need to be discretized for the rule generation. We present a new approach to these problems. Traditional techniques make use of feature merits based on either the information theoretic, or the statistical correlation between each feature and the class. We instead assign merits to features by finding each feature's "obligation" to the class discrimination in the context of other features. The merits are then used to rank the features, select a feature subset, and discretize the numeric variables. Experience with benchmark example sets demonstrates that the new approach is a powerful alternative to the traditional methods. This paper concludes by posing some new technical issues that arise from this approach.
135 citations
Cites background from "Learnability and the Vapnik-Chervon..."
...The parameters at the boundary of failures are meaningful in that they give some concrete values of the number of examples needed for CM to succeed, which we believe is related to the number of examples needed to learn EXOR functions based on the VC dimensions [22] in the presence of random variables....
[...]
References
More filters
01 Jan 1979
42,654 citations
Book•
01 Jan 1979
TL;DR: The second edition of a quarterly column as discussed by the authors provides a continuing update to the list of problems (NP-complete and harder) presented by M. R. Garey and myself in our book "Computers and Intractability: A Guide to the Theory of NP-Completeness,” W. H. Freeman & Co., San Francisco, 1979.
Abstract: This is the second edition of a quarterly column the purpose of which is to provide a continuing update to the list of problems (NP-complete and harder) presented by M. R. Garey and myself in our book ‘‘Computers and Intractability: A Guide to the Theory of NP-Completeness,’’ W. H. Freeman & Co., San Francisco, 1979 (hereinafter referred to as ‘‘[G&J]’’; previous columns will be referred to by their dates). A background equivalent to that provided by [G&J] is assumed. Readers having results they would like mentioned (NP-hardness, PSPACE-hardness, polynomial-time-solvability, etc.), or open problems they would like publicized, should send them to David S. Johnson, Room 2C355, Bell Laboratories, Murray Hill, NJ 07974, including details, or at least sketches, of any new proofs (full papers are preferred). In the case of unpublished results, please state explicitly that you would like the results mentioned in the column. Comments and corrections are also welcome. For more details on the nature of the column and the form of desired submissions, see the December 1981 issue of this journal.
40,020 citations
Book•
01 Jan 1968
TL;DR: The arrangement of this invention provides a strong vibration free hold-down mechanism while avoiding a large pressure drop to the flow of coolant fluid.
Abstract: A fuel pin hold-down and spacing apparatus for use in nuclear reactors is disclosed. Fuel pins forming a hexagonal array are spaced apart from each other and held-down at their lower end, securely attached at two places along their length to one of a plurality of vertically disposed parallel plates arranged in horizontally spaced rows. These plates are in turn spaced apart from each other and held together by a combination of spacing and fastening means. The arrangement of this invention provides a strong vibration free hold-down mechanism while avoiding a large pressure drop to the flow of coolant fluid. This apparatus is particularly useful in connection with liquid cooled reactors such as liquid metal cooled fast breeder reactors.
17,939 citations
14,948 citations
Book•
01 Jan 1973
TL;DR: In this article, a unified, comprehensive and up-to-date treatment of both statistical and descriptive methods for pattern recognition is provided, including Bayesian decision theory, supervised and unsupervised learning, nonparametric techniques, discriminant analysis, clustering, preprosessing of pictorial data, spatial filtering, shape description techniques, perspective transformations, projective invariants, linguistic procedures, and artificial intelligence techniques for scene analysis.
Abstract: Provides a unified, comprehensive and up-to-date treatment of both statistical and descriptive methods for pattern recognition. The topics treated include Bayesian decision theory, supervised and unsupervised learning, nonparametric techniques, discriminant analysis, clustering, preprosessing of pictorial data, spatial filtering, shape description techniques, perspective transformations, projective invariants, linguistic procedures, and artificial intelligence techniques for scene analysis.
13,647 citations