DMCA
Generalised Coupled Tensor Factorisation
BibTeX
@MISC{Kenan_generalisedcoupled,
author = {Y. Kenan and Yılmaz A. Taylan and Cemgil Umut S¸ims¸ekli},
title = {Generalised Coupled Tensor Factorisation},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We derive algorithms for generalised tensor factorisation (GTF) by building upon the well-established theory of Generalised Linear Models. Our algorithms are general in the sense that we can compute arbitrary factorisations in a message passing framework, derived for a broad class of exponential family distributions including special cases such as Tweedie’s distributions corresponding to β-divergences. By bounding the step size of the Fisher Scoring iteration of the GLM, we obtain general updates for real data and multiplicative updates for non-negative data. The GTF framework is, then extended easily to address the problems when multiple observed tensors are factorised simultaneously. We illustrate our coupled factorisation approach on synthetic data as well as on a musical audio restoration problem. 1
Keyphrases
coupled tensor factorisation arbitrary factorisation linear model synthetic data coupled factorisation approach broad class exponential family distribution fisher scoring iteration gtf framework real data well-established theory musical audio restoration problem message passing framework multiplicative update general update non-negative data generalised tensor factorisation step size special case
