Mostra el registre d'ítem simple
A Dichotomy theorem for learning quantified Boolean formulas
dc.contributor.author | Dalmau Lloret, Víctor |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
dc.date.accessioned | 2016-02-26T09:53:16Z |
dc.date.available | 2016-02-26T09:53:16Z |
dc.date.issued | 1997-03 |
dc.identifier.citation | Dalmau, V. "A Dichotomy theorem for learning quantified Boolean formulas". 1997. |
dc.identifier.uri | http://hdl.handle.net/2117/83484 |
dc.description.abstract | We consider the following classes of quantified boolean formulas. Fix a finite set of basic boolean functions. Take conjunctions of these basic functions applied to variables and constants in arbitrary way. Finally quantify existentially or universally some of the variables. We prove the following dichotomy theorem: For any set of basic boolean functions, the resulting set of formulas is either polynomially learnable from equivalence queries alone or else it is not PAC-predictable even with membership queries under cryptographic assumptions. Furthermore we identify precisely which sets of basic functions are in which of the two cases. |
dc.format.extent | 22 p. |
dc.language.iso | eng |
dc.relation.ispartofseries | LSI-97-16-R |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Informàtica teòrica |
dc.subject.other | Dichotomy theorem |
dc.subject.other | Boolean formulas |
dc.title | A Dichotomy theorem for learning quantified Boolean formulas |
dc.type | External research report |
dc.rights.access | Open Access |
local.identifier.drac | 1891392 |
dc.description.version | Postprint (published version) |
local.citation.author | Dalmau, V. |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Reports de recerca [1.107]