English

FMMI: Flow Matching Mutual Information Estimation

Machine Learning 2026-02-10 v2 Information Theory math.IT

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.

Keywords

Cite

@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}
}

Comments

11 pages

R2 v1 2026-07-01T07:32:40.548Z