English

Geometric variational inference

Methodology 2021-07-06 v2 Instrumentation and Methods for Astrophysics Machine Learning

Abstract

Efficiently accessing the information contained in non-linear and high dimensional probability distributions remains a core challenge in modern statistics. Traditionally, estimators that go beyond point estimates are either categorized as Variational Inference (VI) or Markov-Chain Monte-Carlo (MCMC) techniques. While MCMC methods that utilize the geometric properties of continuous probability distributions to increase their efficiency have been proposed, VI methods rarely use the geometry. This work aims to fill this gap and proposes geometric Variational Inference (geoVI), a method based on Riemannian geometry and the Fisher information metric. It is used to construct a coordinate transformation that relates the Riemannian manifold associated with the metric to Euclidean space. The distribution, expressed in the coordinate system induced by the transformation, takes a particularly simple form that allows for an accurate variational approximation by a normal distribution. Furthermore, the algorithmic structure allows for an efficient implementation of geoVI which is demonstrated on multiple examples, ranging from low-dimensional illustrative ones to non-linear, hierarchical Bayesian inverse problems in thousands of dimensions.

Keywords

Cite

@article{arxiv.2105.10470,
  title  = {Geometric variational inference},
  author = {Philipp Frank and Reimar Leike and Torsten A. Enßlin},
  journal= {arXiv preprint arXiv:2105.10470},
  year   = {2021}
}

Comments

42 pages, 18 figures, accepted by Entropy

R2 v1 2026-06-24T02:21:05.791Z