InfoBridge: Mutual Information estimation via Bridge Matching
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 60 of its 102 references that are in the map. First posted on arXiv 3 Feb 2025.
Builds on
60 of 102 references.
References · 60
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2022Classifier-Free Diffusion Guidancecited by 5,847
- 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
- 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
- 2018Deep Graph Infomaxcited by 1,106
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
- 2015Deep Learning and the Information Bottleneck Principlecited by 802
- 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
38 more
- 2018MINE: Mutual Information Neural Estimationcited by 683
- 2019On Mutual Information Maximization for Representation Learningcited by 316
- 2017Information-theoretic analysis of generalization capability of learning algorithmscited by 303
- 2013A survey of the Schr"odinger problem and some of its connections with optimal transportcited by 292
- 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
- 2023Denoising Diffusion Bridge Modelscited by 178
- 2023Diffusion Schr"odinger Bridge Matchingcited by 153
- 2020Reasoning About Generalization via Conditional Mutual Informationcited by 147
- 2021Solving Schr"odinger Bridges via Maximum Likelihoodcited by 141
- 2019Understanding the Limitations of Variational Mutual Information Estimatorscited by 140
- 2020Telescoping Density-Ratio Estimationcited by 108
- 2023Simulation-free Schr"odinger bridges via score and flow matchingcited by 83
- 2023Diffusion Bridge Mixture Transports, Schr"odinger Bridge Problems and Generative Modelingcited by 80
- 2022The Schr"odinger Bridge between Gaussian Measures has a Closed Formcited by 63
- 2021Bayesian Learning via Neural Schr"odinger-F"ollmer Flowscited by 56
- 2023normflows: A PyTorch Package for Normalizing Flowscited by 56
- 2022Entropic Neural Optimal Transport via Diffusion Processescited by 50
- 2024Schr"odinger Bridge Flow for Unpaired Data Translationcited by 47
- 2024Light and Optimal Schr"odinger Bridge Matchingcited by 45
- 2017Model-Powered Conditional Independence Testcited by 43
- 2023Aligned Diffusion Schr"odinger Bridgescited by 38
- 2023Beyond Normal: On the Evaluation of Mutual Information Estimatorscited by 37
- 2023RetroBridge: Modeling Retrosynthesis with Markov Bridgescited by 36
- 2024Simple ReFlow: Improved Techniques for Fast Flow Modelscited by 34
- 2023MINDE: Mutual Information Neural Diffusion Estimationcited by 31
- 2019Quantifying High-order Interdependencies via Multivariate Extensions of the Mutual Informationcited by 30
- 2023Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesiscited by 30
- 2016Efficient multivariate entropy estimation via k-nearest neighbour distancescited by 28
- 2024Consistency Diffusion Bridge Modelscited by 23
- 2017Nonparametric independence testing via mutual informationcited by 22
- 2024Mutual Information Estimation via Normalizing Flowscited by 22
- 2023Augmented Bridge Matchingcited by 21
- 2023Information Bottleneck Analysis of Deep Neural Networks via Lossy Compressioncited by 19
- 2023Building the Bridge of Schr"odinger: A Continuous Entropic Optimal Transport Benchmarkcited by 19
- 2023Light Schr"odinger Bridgecited by 18
- 2018Mutual Information Maximization for Simple and Accurate Part-Of-Speech Inductioncited by 17
- 2023Mutual Information Estimation via f-Divergence and Data Derangementscited by 17
- 2018Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablationcited by 13
50 most cited of 60 All 60 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 6.
7 papers.
- 2025FMMI: Flow Matching Mutual Information Estimationcited by 4
- 2026Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detectioncited by 2
- 2026Discrete Bridges for Mutual Information Estimationcited by 1
- 2026Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standardscited by 1
- 2026Tilted Schr"odinger Bridge Matchingcited by 1
- 2026DIPHINE: Diffusion-based Phi-ID Neural Estimatorcited by 0
- 2026ALICE: In-context, Zero-shot, Mutual Information Estimationcited by 0
- 2026ALICE: In-context, Zero-shot, Mutual Information Estimation28 Sep 2026
- 2026Tilted Schr"odinger Bridge Matching28 Sep 2026
- 2026Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection26 Jun 2026
- 2026DIPHINE: Diffusion-based Phi-ID Neural Estimator17 Jun 2026
- 2026Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards27 Mar 2026
- 2026Discrete Bridges for Mutual Information Estimation9 Feb 2026
- 2025FMMI: Flow Matching Mutual Information Estimation11 Nov 2025