Learnability and the Vapnik-Chervonenkis dimension
Citations
[...]
38,208 citations
19,056 citations
5,506 citations
5,370 citations
3,857 citations
References
9,262 citations
5,311 citations
4,806 citations
3,939 citations
"Learnability and the Vapnik-Chervon..." refers background or methods or result in this paper
...introduced in [29]* to arbitrary probability distributions on E”. For a fixed distribution, an E-transversal for R is a finite set of points N G E” such that every region in R of probability at least E contains at least one point in N. Se:ction A2 uses the notion of an c-transversal to provide the primary machinery for Theorem 2.1, following [29] and [ 62 ]....
[...]
...A2. Proof of Theorem 2.1 (ii)(a) For the next two lemmas let R G 2x be a fixed nonempty class of sets and P be a distribution on X such that QT and Jz” are measurable for all m 2 1 and t > 0. The proofs of these lemmas are analogous to those of Lemma and Theorem 2 of [ 62 ]....
[...]
...To show that these classes are also uniformly learnable, we use a concept first introduced in [ 62 ]....
[...]
...We note only that it employs techniques similar to those used in [ 62 ], which form the basis of Lemmas A2.1 and A2.2 given above....
[...]
...Since the above bound is O( l/c(log( l/6) + n log( l/E))), for small t it is significantly better than the O( l/~‘(log( l/F) + nlog(n/t))) bound given in [51] (eq. 29) derived directly from [ 151 and [ 62 ]....
[...]
2,641 citations
"Learnability and the Vapnik-Chervon..." refers background in this paper
...can easily be shown to be universally separable (see exercises 4, 5 and 7 in chapter II of [ 54 ])....
[...]
...This problem is addressed in [ 171, [ 181, [23], [ 54 ], and [61] from a purely statistical point of view....
[...]
...countably S-coverable in [7a]; see the appendix of [ 54 ] for a discussion of other approaches)....
[...]