General bounds on statistical query learning and PAC learning with noise via hypothesis boosting

Author

Aslam, Javed A. ; Decatur, S.E.

Author_Institution

Lab. for Comput. Sci., MIT, Cambridge, MA, USA

fYear

1993

fDate

3-5 Nov 1993

Firstpage

282

Lastpage

291

Abstract

We derive general bounds on the complexity of learning in the statistical query model and in the PAC model with classification noise. We do so by considering the problem of boosting the accuracy of weak learning algorithms which fall within the statistical query model. This new model was introduced by M. Kearns (1993) to provide a general framework for efficient PAC learning in the presence of classification noise

Keywords

computational complexity; learning (artificial intelligence); PAC learning; complexity; general bounds; hypothesis boosting; noise; statistical query learning; Boosting; Computer science; Contracts; Extraterrestrial measurements; Laboratories; Machine learning; Machine learning algorithms; Noise measurement; Size measurement; Upper bound;

fLanguage

English

Publisher

ieee

Conference_Titel

Foundations of Computer Science, 1993. Proceedings., 34th Annual Symposium on

Conference_Location

Palo Alto, CA

Print_ISBN

0-8186-4370-6

Type

conf

DOI

10.1109/SFCS.1993.366859

Filename

366859

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2366576