Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952130252> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2952130252 abstract "We describe a slightly sub-exponential time algorithm for learning parity functions in the presence of random classification noise. This results in a polynomial-time algorithm for the case of parity functions that depend on only the first O(log n log log n) bits of input. This is the first known instance of an efficient noise-tolerant algorithm for a concept class that is provably not learnable in the Statistical Query model of Kearns. Thus, we demonstrate that the set of problems learnable in the statistical query model is a strict subset of those problems learnable in the presence of noise in the PAC model. In coding-theory terms, what we give is a poly(n)-time algorithm for decoding linear k by n codes in the presence of random noise for the case of k = c log n loglog n for some c > 0. (The case of k = O(log n) is trivial since one can just individually check each of the 2^k possible messages and choose the one that yields the closest codeword.) A natural extension of the statistical query model is to allow queries about statistical properties that involve t-tuples of examples (as opposed to single examples). The second result of this paper is to show that any class of functions learnable (strongly or weakly) with t-wise queries for t = O(log n) is also weakly learnable with standard unary queries. Hence this natural extension to the statistical query model does not increase the set of weakly learnable functions." @default.
- W2952130252 created "2019-06-27" @default.
- W2952130252 creator A5024803432 @default.
- W2952130252 creator A5030116441 @default.
- W2952130252 creator A5086904495 @default.
- W2952130252 date "2000-10-15" @default.
- W2952130252 modified "2023-09-27" @default.
- W2952130252 title "Noise-Tolerant Learning, the Parity Problem, and the Statistical Query Model" @default.
- W2952130252 cites W1481192215 @default.
- W2952130252 cites W1569974224 @default.
- W2952130252 cites W1995897489 @default.
- W2952130252 cites W2064680241 @default.
- W2952130252 cites W2071927551 @default.
- W2952130252 cites W2107189314 @default.
- W2952130252 cites W2126144052 @default.
- W2952130252 hasPublicationYear "2000" @default.
- W2952130252 type Work @default.
- W2952130252 sameAs 2952130252 @default.
- W2952130252 citedByCount "0" @default.
- W2952130252 crossrefType "posted-content" @default.
- W2952130252 hasAuthorship W2952130252A5024803432 @default.
- W2952130252 hasAuthorship W2952130252A5030116441 @default.
- W2952130252 hasAuthorship W2952130252A5086904495 @default.
- W2952130252 hasConcept C105795698 @default.
- W2952130252 hasConcept C109214941 @default.
- W2952130252 hasConcept C11413529 @default.
- W2952130252 hasConcept C114289077 @default.
- W2952130252 hasConcept C114614502 @default.
- W2952130252 hasConcept C118615104 @default.
- W2952130252 hasConcept C118930307 @default.
- W2952130252 hasConcept C121332964 @default.
- W2952130252 hasConcept C134306372 @default.
- W2952130252 hasConcept C151376022 @default.
- W2952130252 hasConcept C153207627 @default.
- W2952130252 hasConcept C2777151079 @default.
- W2952130252 hasConcept C311688 @default.
- W2952130252 hasConcept C33923547 @default.
- W2952130252 hasConcept C57273362 @default.
- W2952130252 hasConcept C63553672 @default.
- W2952130252 hasConcept C78023250 @default.
- W2952130252 hasConceptScore W2952130252C105795698 @default.
- W2952130252 hasConceptScore W2952130252C109214941 @default.
- W2952130252 hasConceptScore W2952130252C11413529 @default.
- W2952130252 hasConceptScore W2952130252C114289077 @default.
- W2952130252 hasConceptScore W2952130252C114614502 @default.
- W2952130252 hasConceptScore W2952130252C118615104 @default.
- W2952130252 hasConceptScore W2952130252C118930307 @default.
- W2952130252 hasConceptScore W2952130252C121332964 @default.
- W2952130252 hasConceptScore W2952130252C134306372 @default.
- W2952130252 hasConceptScore W2952130252C151376022 @default.
- W2952130252 hasConceptScore W2952130252C153207627 @default.
- W2952130252 hasConceptScore W2952130252C2777151079 @default.
- W2952130252 hasConceptScore W2952130252C311688 @default.
- W2952130252 hasConceptScore W2952130252C33923547 @default.
- W2952130252 hasConceptScore W2952130252C57273362 @default.
- W2952130252 hasConceptScore W2952130252C63553672 @default.
- W2952130252 hasConceptScore W2952130252C78023250 @default.
- W2952130252 hasLocation W29521302521 @default.
- W2952130252 hasOpenAccess W2952130252 @default.
- W2952130252 hasPrimaryLocation W29521302521 @default.
- W2952130252 hasRelatedWork W1497325939 @default.
- W2952130252 hasRelatedWork W1965185568 @default.
- W2952130252 hasRelatedWork W2083909116 @default.
- W2952130252 hasRelatedWork W2108680711 @default.
- W2952130252 hasRelatedWork W2111658460 @default.
- W2952130252 hasRelatedWork W2124407183 @default.
- W2952130252 hasRelatedWork W2140152225 @default.
- W2952130252 hasRelatedWork W2405466600 @default.
- W2952130252 hasRelatedWork W2752597570 @default.
- W2952130252 hasRelatedWork W2949361528 @default.
- W2952130252 hasRelatedWork W2949644106 @default.
- W2952130252 hasRelatedWork W2951038604 @default.
- W2952130252 hasRelatedWork W2951825758 @default.
- W2952130252 hasRelatedWork W2951913790 @default.
- W2952130252 hasRelatedWork W2952483363 @default.
- W2952130252 hasRelatedWork W2962888841 @default.
- W2952130252 hasRelatedWork W2989898219 @default.
- W2952130252 hasRelatedWork W3023736834 @default.
- W2952130252 hasRelatedWork W3037469894 @default.
- W2952130252 hasRelatedWork W3099576038 @default.
- W2952130252 isParatext "false" @default.
- W2952130252 isRetracted "false" @default.
- W2952130252 magId "2952130252" @default.
- W2952130252 workType "article" @default.