FMMI: Flow Matching Mutual Information Estimation

Download PDF
Open Webpage

Ivan Butakov, Alexander Semenenko, Alexey A. Frolov, Ivan V. Oseledets

Published: 2025, Last Modified: 27 Jan 2026CoRR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: We introduce a novel Mutual Information (MI) estimator that fundamentally reframes the discriminative approach. Instead of training a classifier to discriminate between joint and marginal distributions, we learn a normalizing flow that transforms one into the other. This technique produces a computationally efficient and precise MI estimate that scales well to high dimensions and across a wide range of ground-truth MI values.