Learning with queries corrupted by classification noise

Jeffrey Jackson, Eli Shamir*, Clara Shwartzman

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Kearns introduced the "statistical query" (SQ) model as a general method for producing learning algorithms which are robust against classification noise. We extend this approach in several ways in order to tackle algorithms that use "membership queries", focusing on the more stringent model of "persistent noise". The main ingredients in the general analysis are: 1. Smallness of dimension of the classes of both the target and the queries. 2. Independence of the noise variables. Persistence restricts independence, forcing repeated invocation of the same point x to give the same label. We apply the general analysis to get a noise-robust version of Jackson's Harmonic Sieve, which learns DNF under the uniform distribution. This corrects an error in his earlier analysis of noise tolerant DNF learning.

Original languageEnglish
Pages (from-to)157-175
Number of pages19
JournalDiscrete Applied Mathematics
Volume92
Issue number2-3
DOIs
StatePublished - Jun 1999

Fingerprint

Dive into the research topics of 'Learning with queries corrupted by classification noise'. Together they form a unique fingerprint.

Cite this