InfoBridge: Mutual Information estimation via Bridge Matching
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914356878376960 |
|---|---|
| author | Kholkin, Sergei Butakov, Ivan Burnaev, Evgeny Gushchin, Nikita Korotin, Alexander |
| author_facet | Kholkin, Sergei Butakov, Ivan Burnaev, Evgeny Gushchin, Nikita Korotin, Alexander |
| contents | Diffusion bridge models have recently become a powerful tool in the field of generative modeling. In this work, we leverage their power to address another important problem in machine learning and information theory, the estimation of the mutual information (MI) between two random variables. Neatly framing MI estimation as a domain transfer problem, we construct an unbiased estimator for data posing difficulties for conventional MI estimators. We showcase the performance of our estimator on three standard MI estimation benchmarks, i.e., low-dimensional, image-based and high MI, and on real-world data, i.e., protein language model embeddings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01383 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InfoBridge: Mutual Information estimation via Bridge Matching Kholkin, Sergei Butakov, Ivan Burnaev, Evgeny Gushchin, Nikita Korotin, Alexander Machine Learning Diffusion bridge models have recently become a powerful tool in the field of generative modeling. In this work, we leverage their power to address another important problem in machine learning and information theory, the estimation of the mutual information (MI) between two random variables. Neatly framing MI estimation as a domain transfer problem, we construct an unbiased estimator for data posing difficulties for conventional MI estimators. We showcase the performance of our estimator on three standard MI estimation benchmarks, i.e., low-dimensional, image-based and high MI, and on real-world data, i.e., protein language model embeddings. |
| title | InfoBridge: Mutual Information estimation via Bridge Matching |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.01383 |