Sauer’s Lemma is extended to classes HN of binary-valued functions h on [n] = {1,..., n} which have a margin less than or equal to N on all x ∈ [n] with h(x) = 1, where the margin µh(x) of h at x ∈ [n] is defined as the largest non-negative integer a such that h is constant on the interval Ia(x) = [x − a, x + a] ⊆ [n]. Estimates are obtained for the cardinality of classes of binary valued functions with a margin of at least N on a positive sample S ⊆ [n]
A number of results have bounded generalization of a classier in terms of its margin on the training...
A number of results have bounded generalization error of a classifier in terms of its margin on the ...
Recently, Brandt, Maus and Uitto [PODC'19] showed that, in a restricted setting, the dependency of t...
AbstractSauer's lemma is extended to classes HN of binary-valued functions h on [n]={1,…,n} which ha...
AbstractLet [n]={1,…,n}. For a function h:[n]→{0,1}, x∈[n] and y∈{0,1} define by the width ωh(x,y) o...
For any class of binary functions on [n] = {1,..., n} a classical result by Sauer states a sufficie...
The Vapnik-Chervonenkis (VC) dimension (also known as the trace number) and the Sauer-Shelah lemma ...
Existing proofs of Vapnik's result on the VC dimension of bounded margin classifiers rely on th...
Let (S,A,P) be a probability space and let Pn be the empirical measure based on i.i.d. sample (X1,.....
This paper collects together a miscellany of results originally motivated by the analysis of the gen...
This paper concerns learning binary-valued functions defined on, and investigates how a particular t...
AbstractWe generalize Sauer's lemma to multivalued functions, proving tight bounds on the cardinalit...
A number of results have bounded generalization of a classier in terms of its margin on the training...
Recent work has introduced Boolean kernels with which one can learn linear threshold functions over ...
AbstractThis paper concerns learning binary-valued functions defined on R, and investigates how a pa...
A number of results have bounded generalization of a classier in terms of its margin on the training...
A number of results have bounded generalization error of a classifier in terms of its margin on the ...
Recently, Brandt, Maus and Uitto [PODC'19] showed that, in a restricted setting, the dependency of t...
AbstractSauer's lemma is extended to classes HN of binary-valued functions h on [n]={1,…,n} which ha...
AbstractLet [n]={1,…,n}. For a function h:[n]→{0,1}, x∈[n] and y∈{0,1} define by the width ωh(x,y) o...
For any class of binary functions on [n] = {1,..., n} a classical result by Sauer states a sufficie...
The Vapnik-Chervonenkis (VC) dimension (also known as the trace number) and the Sauer-Shelah lemma ...
Existing proofs of Vapnik's result on the VC dimension of bounded margin classifiers rely on th...
Let (S,A,P) be a probability space and let Pn be the empirical measure based on i.i.d. sample (X1,.....
This paper collects together a miscellany of results originally motivated by the analysis of the gen...
This paper concerns learning binary-valued functions defined on, and investigates how a particular t...
AbstractWe generalize Sauer's lemma to multivalued functions, proving tight bounds on the cardinalit...
A number of results have bounded generalization of a classier in terms of its margin on the training...
Recent work has introduced Boolean kernels with which one can learn linear threshold functions over ...
AbstractThis paper concerns learning binary-valued functions defined on R, and investigates how a pa...
A number of results have bounded generalization of a classier in terms of its margin on the training...
A number of results have bounded generalization error of a classifier in terms of its margin on the ...
Recently, Brandt, Maus and Uitto [PODC'19] showed that, in a restricted setting, the dependency of t...