A. Gonzalez Sanz

Mean-field variational inference (MFVI) is a workhorse of modern Bayesian computation, yet its fundamental properties remain poorly understood. This talk presents a unified geometric analysis addressing three questions: When is MFVI stable? Why does it collapse modes? And how can we fix it? First, we establish that for strongly log-concave targets, the MFVI optimizer depends Lipschitz continuously on the target distribution in the 2-Wasserstein distance - with a dimension-free constant - and characterize its derivative via a PDE. These results yield new guarantees for robust Bayes and empirical Bayes. Second, we provide the first theoretical explanation of mode collapse: when targeting mixtures, MFVI concentrates mass on a single component. We quantify this phenomenon via a notion of δ-separateness and show that collapse depends critically on component geometry. Finally, we propose Rotational Variational Inference (RoVI) , which augments MFVI with a learnable rotation to capture correlation while retaining tractability. Numerical examples illustrate the theory and the benefits of RoVI.

Keywords: Mean Field Variational Inference Stability Wasserstein Geometry

Scheduled
GT Análisis de Datos Funcionales I
September 4, 2026  9:00 AM
Aula 30

Other papers in the same session


Cookie policy

We use cookies in order to be able to identify and authenticate you on the website. They are necessary for the correct functioning of it, and therefore they can not be disabled. If you continue browsing the website, you are agreeing with their acceptance, as well as our Privacy Policy.

Additionally, we use Google Analytics in order to analyze the website traffic. They also use cookies and you can accept or refuse them with the buttons below.

You can read more details about our Cookie Policy and our Privacy Policy.