Boosting Black-Box Variational Inference by Incorporating the Natural Gradient

Felix  Trusheim; Alexandru Paul Condurache; Alfred Mertins

Boosting Black-Box Variational Inference by Incorporating the Natural Gradient

Felix Trusheim, Alexandru Paul Condurache, Alfred Mertins

Institut für Signalverarbeitung

Abstract

In this paper we present a modification of thepopular Black-Box Variational Inference (BBVI) approachwhich significantly improves the computational efficiency of theinference. We achieve this performance boost by replacing thestandard gradient in the stochastic gradient ascent framework ofBBVI with the natural gradient. Our experimental results (e.g.training of neutral networks) show that the proposed methodoutperforms the original BBVI algorithm on both synthetic andreal data.

Originalsprache	Englisch
Seitenumfang	6
Publikationsstatus	Veröffentlicht - 01.08.2018

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

SDG 9 – Industrie, Innovation und Infrastruktur

Dokumente

https://www.isip.uni-luebeck.de/fileadmin/files/Trusheim2018.pdf

Zitieren

@conference{b68ffd73f8e14ceea5cdcce6e88b2654,

title = "Boosting Black-Box Variational Inference by Incorporating the Natural Gradient",

abstract = "In this paper we present a modification of thepopular Black-Box Variational Inference (BBVI) approachwhich significantly improves the computational efficiency of theinference. We achieve this performance boost by replacing thestandard gradient in the stochastic gradient ascent framework ofBBVI with the natural gradient. Our experimental results (e.g.training of neutral networks) show that the proposed methodoutperforms the original BBVI algorithm on both synthetic andreal data.",

author = "Felix Trusheim and Condurache, \{Alexandru Paul\} and Alfred Mertins",

year = "2018",

month = aug,

day = "1",

language = "English",

}

TY - CONF

T1 - Boosting Black-Box Variational Inference by Incorporating the Natural Gradient

AU - Trusheim, Felix

AU - Condurache, Alexandru Paul

AU - Mertins, Alfred

PY - 2018/8/1

Y1 - 2018/8/1

N2 - In this paper we present a modification of thepopular Black-Box Variational Inference (BBVI) approachwhich significantly improves the computational efficiency of theinference. We achieve this performance boost by replacing thestandard gradient in the stochastic gradient ascent framework ofBBVI with the natural gradient. Our experimental results (e.g.training of neutral networks) show that the proposed methodoutperforms the original BBVI algorithm on both synthetic andreal data.

AB - In this paper we present a modification of thepopular Black-Box Variational Inference (BBVI) approachwhich significantly improves the computational efficiency of theinference. We achieve this performance boost by replacing thestandard gradient in the stochastic gradient ascent framework ofBBVI with the natural gradient. Our experimental results (e.g.training of neutral networks) show that the proposed methodoutperforms the original BBVI algorithm on both synthetic andreal data.

M3 - Conference Papers

ER -

Boosting Black-Box Variational Inference by Incorporating the Natural Gradient

Abstract

UN SDGs

Dokumente

Fingerprint

Zitieren