paper-with-me

Papers

MINDE: Mutual Information Neural Diffusion Estimation

2023-10-13 · Giulio Franzese, Mustapha Bounoua, Pietro Michiardi

In this work we present a new method for the estimation of Mutual Information (MI) between random variables. Our approach is based on an original interpretation of the Girsanov theorem, which allows us to use score-based diffusion models to estimate the Kullback Leibler divergence between two densities as a difference between their score functions. As a by-product, our method also enables the estimation of the entropy of random variables. Armed with such building blocks, we present a general recipe to measure MI, which unfolds in two directions: one uses conditional diffusion process, whereas the other uses joint diffusion processes that allow simultaneous modelling of two random variables. Our results, which derive from a thorough experimental protocol over all the variants of our approach, indicate that our method is more accurate than the main alternatives from the literature, especially for challenging distributions. Furthermore, our methods pass MI self-consistency tests, including data processing and additivity under independence, which instead are a pain-point of existing methods.

📄 PDF Abstract BibTeX arXiv:2310.09031

Code (1)

MustaphaBounoua/minde 공식 구현 jax

Tasks

Mutual Information Estimation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors

2023-05-29 · NeurIPS 2023 11 · Paul S. Scotti, Atmadeep Banerjee, Jimmie Goode, Stepan Shabalin 외

We present MindEye, a novel fMRI-to-image approach to retrieve and reconstruct viewed images from brain activity. Our model comprises two parallel submodules that are specialized for retrieval (using contrastive learning…

Contrastive LearningImage ReconstructionRetrieval

MMG: Mutual Information Estimation via the MMSE Gap in Diffusion

2025-09-24 · Longxuan Yu, Xing Shi, Xianghao Kong, Tong Jia 외 arxiv

Mutual information (MI) is one of the most general ways to measure relationships between random variables, but estimating this quantity for complex systems is challenging. Denoising diffusion models have recently set a n…

Density Estimation

InfoBridge: Mutual Information estimation via Bridge Matching

2025-02-03 · Sergei Kholkin, Ivan Butakov, Evgeny Burnaev, Nikita Gushchin 외

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…

Language ModelingLanguage ModellingMutual Information EstimationProtein Language Model

Discrete Bridges for Mutual Information Estimation

2026-02-09 · Iryna Zabarianska, Sergei Kholkin, Grigoriy Ksenofontov, Ivan Butakov 외 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 match…

Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy

2023-12-04 · Danqi Liao, Chen Liu, Benjamin W. Christensen, Alexander Tong 외

Entropy and mutual information in neural networks provide rich information on the learning process, but they have proven difficult to compute reliably in high dimensions. Indeed, in noisy and high-dimensional data, tradi…