{"ID":2843570,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.08552","arxiv_id":"2511.08552","title":"FMMI: Flow Matching Mutual Information Estimation","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.","short_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 a...","url_abs":"https://arxiv.org/abs/2511.08552","url_pdf":"https://arxiv.org/pdf/2511.08552v2","authors":"[\"Ivan Butakov\",\"Alexander Semenenko\",\"Valeriya Kirova\",\"Alexey Frolov\",\"Ivan Oseledets\"]","published":"2025-11-11T18:34:33Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.IT\"]","methods":"[]","has_code":false}