Learning from rounded-off data

Dennis Cheung, Felipe Cucker

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

Abstract

We provide an algorithm to PAC learn multivariate polynomials with real coefficients. The instance space from which labeled samples are drawn is ℝV but the coordinates of such samples are known only approximately. The algorithm is iterative and the main ingredient of its complexity, the number of iterations it performs, is estimated using the condition number of a linear programming problem associated to the sample. To the best of our knowledge, this is the first study of PAC learning concepts parameterized by real numbers from approximate data.
Original languageEnglish
Pages (from-to)1-13
JournalInformation and Computation
Volume182
Issue number1
DOIs
Publication statusPublished - 10 Apr 2003

Fingerprint

Dive into the research topics of 'Learning from rounded-off data'. Together they form a unique fingerprint.

Cite this