Riemannian Laplace Approximation with the Fisher Metric

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yu, Hanlin, Hartmann, Marcelo, Williams, Bernardo, Girolami, Mark, Klami, Arto
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918382133051392
author Yu, Hanlin
Hartmann, Marcelo
Williams, Bernardo
Girolami, Mark
Klami, Arto
author_facet Yu, Hanlin
Hartmann, Marcelo
Williams, Bernardo
Girolami, Mark
Klami, Arto
contents Laplace's method approximates a target density with a Gaussian distribution at its mode. It is computationally efficient and asymptotically exact for Bayesian inference due to the Bernstein-von Mises theorem, but for complex targets and finite-data posteriors it is often too crude an approximation. A recent generalization of the Laplace Approximation transforms the Gaussian approximation according to a chosen Riemannian geometry providing a richer approximation family, while still retaining computational efficiency. However, as shown here, its properties depend heavily on the chosen metric, indeed the metric adopted in previous work results in approximations that are overly narrow as well as being biased even at the limit of infinite data. We correct this shortcoming by developing the approximation family further, deriving two alternative variants that are exact at the limit of infinite data, extending the theoretical analysis of the method, and demonstrating practical improvements in a range of experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2311_02766
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Riemannian Laplace Approximation with the Fisher Metric
Yu, Hanlin
Hartmann, Marcelo
Williams, Bernardo
Girolami, Mark
Klami, Arto
Machine Learning
Methodology
Laplace's method approximates a target density with a Gaussian distribution at its mode. It is computationally efficient and asymptotically exact for Bayesian inference due to the Bernstein-von Mises theorem, but for complex targets and finite-data posteriors it is often too crude an approximation. A recent generalization of the Laplace Approximation transforms the Gaussian approximation according to a chosen Riemannian geometry providing a richer approximation family, while still retaining computational efficiency. However, as shown here, its properties depend heavily on the chosen metric, indeed the metric adopted in previous work results in approximations that are overly narrow as well as being biased even at the limit of infinite data. We correct this shortcoming by developing the approximation family further, deriving two alternative variants that are exact at the limit of infinite data, extending the theoretical analysis of the method, and demonstrating practical improvements in a range of experiments.
title Riemannian Laplace Approximation with the Fisher Metric
topic Machine Learning
Methodology
url https://arxiv.org/abs/2311.02766