The Vapnik-Chervonenkis (VC) dimension (also known as the trace number) and the Sauer-Shelah lemma have found applications in numerous areas including set theory, combinatorial geometry, graph theory and statistical learning theory. Estimation of the complexity of discrete structures associated with the search space of algorithms often amounts to estimating the cardinality of a simpler class which is e#ectively induced by some restrictive property of the search. In this paper we study the complexity of Boolean-function classes of finite VC-dimension which satisfy a local `smoothness' property expressed as having long runs of repeated values. As in Sauer's lemma, a bound is obtained on the cardinality of such classes
CombinatoricsFor any class of binary functions on [n]={1, ..., n} a classical result by Sauer states...
Abstract. The Vapnik-Chervonenkis (VC) dimension plays an important role in statistical learning the...
AbstractA consistent learning algorithm can reconstruct any Boolean function belonging to a given cl...
In this paper, we introduce the discretized-Vapnik-Chervonenkis (VC) dimension for studying the comp...
Lecture Notes in Artificial Intelligence 744, 279-287, 1993The Vapnik-Chervonenkis (VC) dimension is...
We show that the Vapnik-Chervonenkis dimension of Boolean monomials over n variables is at most n fo...
In this paper, we introduce the discretized-Vapnik-Chervonenkis (VC) dimension for studying the comp...
AbstractIn the PAC-learning model, the Vapnik-Chervonenkis (VC) dimension plays the key role to esti...
In the PAC-learning model, the Vapnik-Chervonenkis (VC) dimension plays the key role to estimate the...
The Vapnik-Chervonenkis (VC) dimension is used to measure the complexity of a function class and pla...
Proc. European Conference on Machine Learning, Lecture Notes in Artificial Intelligence 784, 415-418...
We define in this work a new localized version of a Vapnik-Chervonenkis (VC) complexity, namely the ...
AbstractSauer's lemma is extended to classes HN of binary-valued functions h on [n]={1,…,n} which ha...
Sauer’s Lemma is extended to classes HN of binary-valued functions h on [n] = {1,..., n} which have ...
We study the complexity of approximating the VC dimension of a collection of sets, when the sets are...
CombinatoricsFor any class of binary functions on [n]={1, ..., n} a classical result by Sauer states...
Abstract. The Vapnik-Chervonenkis (VC) dimension plays an important role in statistical learning the...
AbstractA consistent learning algorithm can reconstruct any Boolean function belonging to a given cl...
In this paper, we introduce the discretized-Vapnik-Chervonenkis (VC) dimension for studying the comp...
Lecture Notes in Artificial Intelligence 744, 279-287, 1993The Vapnik-Chervonenkis (VC) dimension is...
We show that the Vapnik-Chervonenkis dimension of Boolean monomials over n variables is at most n fo...
In this paper, we introduce the discretized-Vapnik-Chervonenkis (VC) dimension for studying the comp...
AbstractIn the PAC-learning model, the Vapnik-Chervonenkis (VC) dimension plays the key role to esti...
In the PAC-learning model, the Vapnik-Chervonenkis (VC) dimension plays the key role to estimate the...
The Vapnik-Chervonenkis (VC) dimension is used to measure the complexity of a function class and pla...
Proc. European Conference on Machine Learning, Lecture Notes in Artificial Intelligence 784, 415-418...
We define in this work a new localized version of a Vapnik-Chervonenkis (VC) complexity, namely the ...
AbstractSauer's lemma is extended to classes HN of binary-valued functions h on [n]={1,…,n} which ha...
Sauer’s Lemma is extended to classes HN of binary-valued functions h on [n] = {1,..., n} which have ...
We study the complexity of approximating the VC dimension of a collection of sets, when the sets are...
CombinatoricsFor any class of binary functions on [n]={1, ..., n} a classical result by Sauer states...
Abstract. The Vapnik-Chervonenkis (VC) dimension plays an important role in statistical learning the...
AbstractA consistent learning algorithm can reconstruct any Boolean function belonging to a given cl...