With friends at the University of Warwick (in particular, Rocco Caprio and @adriencorenflos.bsky.social), we've recently arXived some work (arxiv.org/abs/2605.30253) on a method for approximate inference known as "Coordinate Ascent Variational Inference", or "CAVI" for short. …
AI Weekly's analysis
→
- The paper establishes Wasserstein contraction of coordinate ascent variational inference without assuming global strong log-concavity of the target.
- The conditions are a functional smoothness of the optimality maps plus a transportation-information inequality at their fixed points.
- Covered models include Ising and Curie-Weiss, Bayesian Gaussian mixtures, high-dimensional Bayesian probit regression, and Pólya-Gamma logistic regression.
Read full analysis →