Benutzer: Gast  Login
Titel:

Generalized Score Matching for Non-Negative Data

Dokumenttyp:
Zeitschriftenaufsatz
Autor(en):
Yu, Shiqing; Drton, Mathias; Shojaie, Ali
Abstract:
A common challenge in estimating parameters of probability density functions is the intractability of the normalizing constant. While in such cases maximum likelihood estimation may be implemented using numerical integration, the approach becomes computationally intensive. The score matching method of Hyvärinen [2005] avoids direct calculation of the normalizing constant and yields closed-form estimates for exponential families of continuous distributions over . Hyvärinen [2007] extended the app...     »
Stichworte:
exponential family, graphical model, positive data, score matching, sparsity
Dewey Dezimalklassifikation:
510 Mathematik
Zeitschriftentitel:
Journal of Machine Learning Research
Jahr:
2019
Band / Volume:
20
Jahr / Monat:
2019-04
Quartal:
2. Quartal
Monat:
Dec
Heft / Issue:
76
Seitenangaben Beitrag:
1-70
Sprache:
en
WWW:
Journal of Machine Learning Research
Eingereicht (bei Zeitschrift):
01.05.2018
Publikationsdatum:
15.04.2019
Semester:
SS 19
Format:
Text
 BibTeX