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 quantiAes 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 Arst provably sublinear (1 ± ϵ)-coreset.
On coresets for logistic regression / Munteanu, A.; Schwiegelshohn, C.; Sohler, C.; Woodruff, D. P.. - 294:(2019), pp. 267-268. (Intervento presentato al convegno 49. Jahrestagung der Gesellschaft fur Informatik: 50 Jahre Gesellschaft fur Informatik - Informatik fur Gesellschaft, INFORMATIK 2019 - 49th Annual Meeting of the German Informatics Society: 50 years of the German Informatics Society - Computer Science for Society, INFORMATICS 2019 tenutosi a Kassel; Germany) [10.18420/inf2019_37].
On coresets for logistic regression
Schwiegelshohn C.;Sohler C.;
2019
Abstract
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 quantiAes 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 Arst provably sublinear (1 ± ϵ)-coreset.| File | Dimensione | Formato | |
|---|---|---|---|
|
Munteanu_On-coresets_2019.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Creative commons
Dimensione
77.01 kB
Formato
Adobe PDF
|
77.01 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
