Beyond EM: A faster Bayesian linear regression algorithm without matrix inversions

•We propose a novel matrix inversion free algorithm for solving the Bayesian linear regression problem with Gaussian priors.•Compared with the conventional gradient based and EM algorithms, our proposed one runs significantly faster while achieving the similar precision performance.•An iterative met...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neurocomputing (Amsterdam) Ročník 378; s. 435 - 440
Hlavní autor: Tang, Ying
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 22.02.2020
Témata:
Bayesian linear regression
Gaussian prior
Matrix-inversion-free
Matrix-inversion-free
Bayesian linear regression
Gaussian prior
ISSN:0925-2312, 1872-8286
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•We propose a novel matrix inversion free algorithm for solving the Bayesian linear regression problem with Gaussian priors.•Compared with the conventional gradient based and EM algorithms, our proposed one runs significantly faster while achieving the similar precision performance.•An iterative method from a perspective of latent matrices is proposed for optimal search without breaking the symmetric positive definite manifold constraint. The Bayesian linear regression is a useful tool for many scientific communities. This paper presents a novel algorithm for solving the Bayesian linear regression problem with Gaussian priors, which shares the same spirit as the gradient based methods. In addition, the standard scheme for this task, the Expectation Maximization (EM) algorithm, involves matrix inversions but our proposed algorithm is free of. Numerical experiments demonstrate that the proposed algorithm performs as well as the gradient based and EM algorithms in term of precision, but runs significantly faster than the gradient based and EM algorithms. Due to its matrix-inversion-free nature, the algorithm of this paper is a viable alternative to the competing methods available in the literature.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2019.10.061