Structural analysis of polynomial time query learnability

For some representation classes, we relate its polynomial time query learnability to the complexity of representation finding problems of P/poly oracles. For example, for CIR, a representation class by logical circuits, the following relations are proved: If for some A ¿ P/poly, the representation f...

Descripción completa

Detalles Bibliográficos
Autores: Watanabe, Osamu, Gavaldà Mestre, Ricard|||0000-0003-4736-7179
Tipo de recurso: informe técnico
Fecha de publicación:1992
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/368978
Acceso en línea:https://hdl.handle.net/2117/368978
Access Level:acceso abierto
Palabra clave:Computational complexity
Complexitat computacional
Àrees temàtiques de la UPC::Informàtica
Descripción
Sumario:For some representation classes, we relate its polynomial time query learnability to the complexity of representation finding problems of P/poly oracles. For example, for CIR, a representation class by logical circuits, the following relations are proved: If for some A ¿ P/poly, the representation finding problem of A is not in Pnpa1, then CIR is not polynomial time query learnable even by using any sorts of queries considered in [Ang88]. On the other hand, if a certain representation subclass of CIR is not polynomial time query learnable by using subset and superset queries, then some B ¿ P/poly exists such that its representation finding problem is not in Pnpb1.