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.
@article{arxiv.2511.08552,
title = {FMMI: Flow Matching Mutual Information Estimation},
author = {Ivan Butakov and Alexander Semenenko and Valeriya Kirova and Alexey Frolov and Ivan Oseledets},
journal= {arXiv preprint arXiv:2511.08552},
year = {2026}
}