mlsanityData to 7 Oct 2026

Discrete Bridges for Mutual Information Estimation

arXiv 2602.08894 ↗First posted 9 Feb 2026cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Diffusion bridge models in both continuous and discrete state spaces have recently become powerful tools in the field of generative modeling. In this work, we leverage the discrete state space formulation of bridge matching models to address another important problem in machine learning and information theory: the estimation of the mutual information (MI) between discrete random variables. By neatly framing MI estimation as a domain transfer problem, we construct a Discrete Bridge Mutual Information (DBMI) estimator suitable for discrete data, which poses difficulties for conventional MI estimators. We showcase the performance of our estimator on two MI estimation settings: low-dimensional and image-based.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

28 of 42 references.

References · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  4. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  5. 2024Simple and Effective Masked Diffusion Language Modelscited by 800
  6. 2018MINE: Mutual Information Neural Estimationcited by 680
  7. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  8. 2022A Continuous Time Framework for Discrete Denoising Modelscited by 437
  9. 2024Discrete Flow Matchingcited by 301
  10. 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
  11. 2023Denoising Diffusion Bridge Modelscited by 171
  12. 2018Chaining Mutual Information and Tightening Generalization Boundscited by 65
16 more
  1. 2022The Schr"odinger Bridge between Gaussian Measures has a Closed Formcited by 63
  2. 2021Bayesian Learning via Neural Schr"odinger-F"ollmer Flowscited by 56
  3. 2024Light and Optimal Schr"odinger Bridge Matchingcited by 45
  4. 2023RetroBridge: Modeling Retrosynthesis with Markov Bridgescited by 35
  5. 2023MINDE: Mutual Information Neural Diffusion Estimationcited by 31
  6. 2024Mutual Information Estimation via Normalizing Flowscited by 22
  7. 2024Discrete Diffusion Schr"odinger Bridge Matching for Graph Transformationcited by 21
  8. 2023Information Bottleneck Analysis of Deep Neural Networks via Lossy Compressioncited by 19
  9. 2023Mutual Information Estimation via f-Divergence and Data Derangementscited by 17
  10. 2025Exponential Family Variational Flow Matching for Tabular Data Generationcited by 15
  11. 2024A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasetscited by 10
  12. 2022Conditional Independence Testing via Latent Representation Learningcited by 9
  13. 2025InfoBridge: Mutual Information estimation via Bridge Matchingcited by 7
  14. 2024textttCOSMIC: Mutual Information for Task-Agnostic Summarization Evaluationcited by 6
  15. 2024Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMaxcited by 4
  16. 2025INFO-SEDD: Continuous Time Markov Chains as Scalable Information Metrics Estimatorscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Tilted Schr"odinger Bridge Matchingcited by 0