Logo des Repositoriums
 
Konferenzbeitrag

On Coresets for Logistic Regression

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2019

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

Coresets are one of the central methods to facilitate the analysis of large data.We continue a recent line of research applying the theory of coresets to logistic regression. First, we show the negative result that no strongly sublinear sized coresets exist for logistic regression. To deal with intractable worst-case instances we introduce a complexity measure µ(X), which quantifies the hardness of compressing a data set for logistic regression. µ(X) has an intuitive statistical interpretation that may be of independent interest. For data sets with bounded µ(X)-complexity, we show that a novel sensitivity sampling scheme produces the first provably sublinear (1 ± ")-coreset.

Beschreibung

Munteanu, Alexander; Schwiegelshohn, Chris; Sohler, Christian; Woodruff, David P. (2019): On Coresets for Logistic Regression. INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft. DOI: 10.18420/inf2019_37. Bonn: Gesellschaft für Informatik e.V.. PISSN: 1617-5468. ISBN: 978-3-88579-688-6. pp. 267-268. Data Science. Kassel. 23.-26. September 2019

Zitierform

Tags