134 search results - page 4 / 27 » On the Complexity of Approximating the VC Dimension |
JALC
2007
13 years 5 months ago
2007
We determine the complexity of learning problems for unary regular languages. We begin by investigating the minimum consistent dfa (resp. nfa) problem which is known not to be app...
CORR
2008
Springer
13 years 5 months ago
2008
Springer
Statistical learning theory chiefly studies restricted hypothesis classes, particularly those with finite Vapnik-Chervonenkis (VC) dimension. The fundamental quantity of interest i...
NIPS
2007
13 years 7 months ago
2007
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of C...
COMPGEOM
2007
ACM
13 years 9 months ago
2007
ACM
The paper consists of two major parts. In the first part, we re-examine relative -approximations, previously studied in [12, 13, 18, 25], and their relation to certain geometric p...
COLT
2000
Springer
13 years 10 months ago
2000
Springer
We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalizatio...