paper-with-me

Papers

Variational inference via radial transport

2026-02-19 · Luca Ghafourpour, Sinho Chewi, Alessio Figalli, Aram-Alexandre Pooladian arxiv

In variational inference (VI), the practitioner approximates a high-dimensional distribution $π$ with a simple surrogate one, often a (product) Gaussian distribution. However, in many cases of practical interest, Gaussian distributions might not capture the correct radial profile of $π$, resulting in poor coverage. In this work, we approach the VI problem from the perspective of optimizing over these radial profiles. Our algorithm radVI is a cheap, effective add-on to many existing VI schemes, such as Gaussian (mean-field) VI and Laplace approximation. We provide theoretical convergence guarantees for our algorithm, owing to recent developments in optimization over the Wasserstein space--the space of probability distributions endowed with the Wasserstein distance--and new regularity properties of radial transport maps in the style of Caffarelli (2000).

📄 PDF Abstract BibTeX arXiv:2602.17525

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning

2019-07-01 · Sebastian Farquhar, Michael Osborne, Yarin Gal

We propose Radial Bayesian Neural Networks (BNNs): a variational approximate posterior for BNNs which scales well to large models while maintaining a distribution over weight-space with full support. Other scalable Bayes…

Continual LearningVariational Inference

Wasserstein variational gradient descent: From semi-discrete optimal transport to ensemble variational inference

2018-11-07 · Luca Ambrogioni, Umut Guclu, Marcel van Gerven

Particle-based variational inference offers a flexible way of approximating complex posterior distributions with a set of particles. In this paper we introduce a new particle-based variational inference method based on t…

Variational Inference

Transport Score Climbing: Variational Inference Using Forward KL and Adaptive Neural Transport

2022-02-03 · Liyi Zhang, David M. Blei, Christian A. Naesseth

Variational inference often minimizes the "reverse" Kullbeck-Leibler (KL) KL(q||p) from the approximate distribution q to the posterior p. Recent work studies the "forward" KL KL(p||q), which unlike reverse KL does not l…

Variational Inference

Correcting Source Mismatch in Flow Matching with Radial-Angular Transport

2026-04-05 · Fouad Oubari, Mathilde Mougeot arxiv

Flow Matching is typically built from Gaussian sources and Euclidean probability paths. For heavy-tailed or anisotropic data, however, a Gaussian source induces a structural mismatch already at the level of the radial di…

Radial and Directional Posteriors for Bayesian Neural Networks

2019-02-07 · Changyong Oh, Kamil Adamczewski, Mijung Park

We propose a new variational family for Bayesian neural networks. We decompose the variational posterior into two components, where the radial component captures the strength of each neuron in terms of its magnitude; whi…