Exploiting tensor rank-one decomposition in probabilistic interence

Title:

Exploiting tensor rank-one decomposition in probabilistic interence

Creator:

Savický, Petr and Vomlel, Jiří

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:cee39902-2186-4a9a-95de-29d643f12f1d
uuid:cee39902-2186-4a9a-95de-29d643f12f1d

Subject:

graphical probabilistic models, probabilistic inference, and tensor rank

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

We propose a new additive decomposition of probability tables - {\em tensor rank-one decomposition}. The basic idea is to decompose a {\em probability table} into a series of tables, such that the table that is the sum of the series is equal to the original table. Each table in the series has the same domain as the original table but can be expressed as a product of one-dimensional tables. Entries in tables are allowed to be any real number, i. e. they can be also negative numbers. The possibility of having negative numbers, in contrast to a multiplicative decomposition, opens new possibilities for a compact representation of probability tables. We show that {\em tensor rank-one decomposition} can be used to reduce the space and time requirements in probabilistic inference. We provide a closed form solution for minimal tensor rank-one decomposition for some special tables and propose a numerical algorithm that can be used in cases when the closed form solution is not known.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Coverage:

[747]-764

Source:

Kybernetika | 2007 Volume:43 | Number:5

Harvested from:

CDK

Metadata only:

false