English

A Geometric Variational Approach to Bayesian Inference

Methodology 2019-03-29 v2

Abstract

We propose a novel Riemannian geometric framework for variational inference in Bayesian models based on the nonparametric Fisher-Rao metric on the manifold of probability density functions. Under the square-root density representation, the manifold can be identified with the positive orthant of the unit hypersphere in L2, and the Fisher-Rao metric reduces to the standard L2 metric. Exploiting such a Riemannian structure, we formulate the task of approximating the posterior distribution as a variational problem on the hypersphere based on the alpha-divergence. This provides a tighter lower bound on the marginal distribution when compared to, and a corresponding upper bound unavailable with, approaches based on the Kullback-Leibler divergence. We propose a novel gradient-based algorithm for the variational problem based on Frechet derivative operators motivated by the geometry of the Hilbert sphere, and examine its properties. Through simulations and real-data applications, we demonstrate the utility of the proposed geometric framework and algorithm on several Bayesian models.

Keywords

Cite

@article{arxiv.1707.09714,
  title  = {A Geometric Variational Approach to Bayesian Inference},
  author = {Abhijoy Saha and Karthik Bharath and Sebastian Kurtek},
  journal= {arXiv preprint arXiv:1707.09714},
  year   = {2019}
}
R2 v1 2026-06-22T21:01:56.241Z