Learnability and the Vapnik-Chervonenkis dimension
Citations
90 citations
90 citations
Cites background or methods from "Learnability and the Vapnik-Chervon..."
...Since (a) holds for the Total Recall algorithm, we can apply the following result of (Blumer et al. 1989): THEOREM 2....
[...]
...A very important combinatorial parameter used to estimate the complexity of learning a concept class is its Vapnik-Chervonenkis dimension (see (Vapnik and Chervonenkis, 1971; Haussler and Welzl, 1987; Pearl, 1978; Blumer et al. 1989))....
[...]
...…1988; Littlestone, 1988; Blumer, Ehrenfeucht, Haussler & Warmuth, 1989; Haussler, 1989), and learnability of concept classes has been characterized (Blumer et al., 1989) using the Vapnik-Chervonenkis (VC) dimension (Vapnik and Chervonenkis, 1971), no practical algorithms have been found for many…...
[...]
90 citations
Cites background or methods from "Learnability and the Vapnik-Chervon..."
...These both implycapw∗,D(ǫ) = O(C 1/2 √ d log(1/ǫ))....
[...]
...…bound can be improved to match the lower bound via a polynomial-time algorithm is been long-standing open question, both for general distributions (Ehrenfeucht et al., 1989; Blumer et al., 1989) and for the case of the uniform distribution in the unit ball (Long, 1995, 2003; Bshouty et al., 2009)....
[...]
...In this section we consider a variant of the Tsybakov noise conditi n (Mammen and Tsybakov, 1999)....
[...]
...Keywords: Active learning, PAC learning, ERM, nearly log-concave distributions, Tsybakov lownoise condition, agnostic learning....
[...]
...(Blumer et al., 1989) achieved polynomial-time learning by finding a consistenthypothesis (i.e., a hypothesis which correctly classifies all training examples); this is a special case of ERM (Vapnik, 1982)....
[...]
89 citations
Cites background from "Learnability and the Vapnik-Chervon..."
...Since the lower bound of [11] is known to be nearly optimal for classical PAC learning algorithms (an upper bound of O( 12 log 1 δ + d 2 log 1 2 ) was given by [6]), our new quantum lower bound is not far from being the best possible....
[...]
...(ii) [6] Any concept class C of VC dimension d can be (2, δ)PAC learned by a classical algorithm with sample complexity O( 12 log 1 δ + d 2 log 1 2 )....
[...]
...For nontrivial concept classes [6] gave a classical sample complexity lower bound of Ω( 12 log 1 δ )....
[...]
89 citations
References
42,654 citations
40,020 citations
17,939 citations
14,948 citations
13,647 citations