FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1517526469> ?p ?o ?g. }

• W1517526469 abstract "The Kushilevitz-Mansour (KM) algorithm is an algorithm that finds all the large Fourier coefficients of a Boolean function. It is the main tool for learning decision trees and DNF expressions in the PAC model with respect to the uniform distribution. The algorithm requires access to the membership query (MQ) oracle. The access is often unavailable in learning applications and thus the KM algorithm cannot be used. We significantly weaken this requirement by producing an analogue of the KM algorithm that uses extended statistical queries (SQ) (SQs in which the expectation is taken with respect to a distribution given by a learning algorithm). We restrict a set of distributions that a learning algorithm may use for its statistical queries to be a set of product distributions with each bit being 1 with probability ρ, 1/2 or 1-ρ for a constant 1/2 > ρ > 0 (we denote the resulting model by SQ-Dρ). Our analogue finds all the large Fourier coefficients of degree lower than clog(n) (we call it the Bounded Sieve (BS)). We use BS to learn decision trees and by adapting Freund's boosting technique we give an algorithm that learns DNF in SQ-Dρ. An important property of the model is that its algorithms can be simulated by MQs with persistent noise. With some modifications BS can also be simulated by MQs with product attribute noise (i.e., for a query x oracle changes every bit of x with some constant probability and calculates the value of the target function at the resulting point) and classification noise. This implies learnability of decision trees and weak learnability of DNF with this non-trivial noise. In the second part of this paper we develop a characterization for learnability with these extended statistical queries. We show that our characterization when applied to SQ-Dρ is tight in terms of learning parity functions. We extend the result given by Blum et al. by proving that there is a class learnable in the PAC model with random classification noise and not learnable in SQ-Dρ." @default.
• W1517526469 created "2016-06-24" @default.
• W1517526469 creator A5017977075 @default.
• W1517526469 creator A5054675941 @default.
• W1517526469 date "2000-01-01" @default.
• W1517526469 modified "2023-10-16" @default.
• W1517526469 title "10.1162/153244302760200669" @default.
• W1517526469 cites W1488301720 @default.
• W1517526469 cites W1507495319 @default.
• W1517526469 cites W1557468152 @default.
• W1517526469 cites W1899006432 @default.
• W1517526469 cites W1974411071 @default.
• W1517526469 cites W1974572210 @default.
• W1517526469 cites W1982003460 @default.
• W1517526469 cites W1982381767 @default.
• W1517526469 cites W2018908820 @default.
• W1517526469 cites W2021885139 @default.
• W1517526469 cites W2027528470 @default.
• W1517526469 cites W2053817819 @default.
• W1517526469 cites W2064680241 @default.
• W1517526469 cites W2088390444 @default.
• W1517526469 cites W2106435708 @default.
• W1517526469 cites W2118991990 @default.
• W1517526469 cites W2123974195 @default.
• W1517526469 cites W2124407183 @default.
• W1517526469 cites W2126144052 @default.
• W1517526469 cites W2158187617 @default.
• W1517526469 cites W2160163251 @default.
• W1517526469 cites W4238893454 @default.
• W1517526469 cites W4248437541 @default.
• W1517526469 doi "https://doi.org/10.1162/153244302760200669" @default.
• W1517526469 hasPublicationYear "2000" @default.
• W1517526469 type Work @default.
• W1517526469 sameAs 1517526469 @default.
• W1517526469 citedByCount "52" @default.
• W1517526469 countsByYear W15175264692012 @default.
• W1517526469 countsByYear W15175264692013 @default.
• W1517526469 countsByYear W15175264692014 @default.
• W1517526469 countsByYear W15175264692015 @default.
• W1517526469 countsByYear W15175264692016 @default.
• W1517526469 countsByYear W15175264692017 @default.
• W1517526469 countsByYear W15175264692018 @default.
• W1517526469 countsByYear W15175264692019 @default.
• W1517526469 countsByYear W15175264692020 @default.
• W1517526469 countsByYear W15175264692021 @default.
• W1517526469 crossrefType "journal-article" @default.
• W1517526469 hasAuthorship W1517526469A5017977075 @default.
• W1517526469 hasAuthorship W1517526469A5054675941 @default.
• W1517526469 hasConcept C185592680 @default.
• W1517526469 hasConcept C192562407 @default.
• W1517526469 hasConceptScore W1517526469C185592680 @default.
• W1517526469 hasConceptScore W1517526469C192562407 @default.
• W1517526469 hasLocation W15175264691 @default.
• W1517526469 hasOpenAccess W1517526469 @default.
• W1517526469 hasPrimaryLocation W15175264691 @default.
• W1517526469 hasRelatedWork W1531601525 @default.
• W1517526469 hasRelatedWork W1990781990 @default.
• W1517526469 hasRelatedWork W2314643286 @default.
• W1517526469 hasRelatedWork W2606768298 @default.
• W1517526469 hasRelatedWork W2606769243 @default.
• W1517526469 hasRelatedWork W2606837276 @default.
• W1517526469 hasRelatedWork W2748952813 @default.
• W1517526469 hasRelatedWork W2899084033 @default.
• W1517526469 hasRelatedWork W2948807893 @default.
• W1517526469 hasRelatedWork W2778153218 @default.
• W1517526469 hasVolume "1" @default.
• W1517526469 isParatext "false" @default.
• W1517526469 isRetracted "false" @default.
• W1517526469 magId "1517526469" @default.
• W1517526469 workType "article" @default.