paper-with-me

홈 › Papers

MINE: Mutual Information Neural Estimation

2018-01-12 · Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, R. Devon Hjelm

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, and strongly consistent. We present a handful of applications on which MINE can be used to minimize or maximize mutual information. We apply MINE to improve adversarially trained generative models. We also use MINE to implement Information Bottleneck, applying it to supervised classification; our results demonstrate substantial improvement in flexibility and performance in these settings.

📄 PDF Abstract BibTeX arXiv:1801.04062

Code (23)

Avi-avidan/MINE pytorch
ChengzhangZhu/MINE tf
DorTsur/SimpleMINEJAX jax
MasanoriYamada/Mine_pytorch pytorch
ReyesDeJong/MINE tf
RickFri/MINE-Mutual-Information-Neural-Estimator tf
ahujak/KKLE
burklight/MINE-PyTorch pytorch
cbg-ethz/bmi jax
csliuwei/Emotion_MI
dizcza/EmbedderSDR pytorch
dizcza/pytorch-mighty pytorch
gtegner/hyper-gan pytorch
gtegner/mine-pytorch pytorch
mboudiaf/Mutual-Information-Variational-Bounds tf
mohith-sakthivel/mine-pytorch pytorch
mzgubic/MINE tf
pecholal/main-vc pytorch
personads/synvae tf
sambklein/MINE_demo tf
shannonycj/simple-mine tf
sungyubkim/MINE-Mutual-Information-Neural-Estimation- pytorch
wushuaida/Implementation-of-Mutual-Information-Neural-Estimator pytorch

Tasks

General Classification

Similar Papers 제목 키워드 기반

Mutual Information Neural Estimation

2018-07-01 · ICML 2018 7 · Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeshwar, Sherjil Ozair 외

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MIN…

General ClassificationMutual Information Estimation

Neural Entropic Estimation: A faster path to mutual information estimation

2019-05-30 · Chung Chan, Ali Al-Bashabsheh, Hing Pang Huang, Michael Lim 외

We point out a limitation of the mutual information neural estimation (MINE) where the network fails to learn at the initial training phase, leading to slow convergence in the number of training iterations. To solve this…

Mutual Information Estimation

NMINE: Normalized Mutual Information Neural Estimation

2026-07-30 · Petra Eerikinharju, Marko Tuononen, Ville Hautamäki arxiv

Mutual information is a general measure of statistical dependence that captures both linear and nonlinear relationships between random variables. For continuous and multidimensional variables For continuous multidimensio…

Interpretable Machine Learning

Learning gradient-based ICA by neurally estimating mutual information

2019-04-22 · Hlynur Davíð Hlynsson, Laurenz Wiskott

Several methods of estimating the mutual information of random variables have been developed in recent years. They can prove valuable for novel approaches to learning statistically independent features. In this paper, we…

blind source separation

MINERVA: Mutual Information Neural Estimation for Supervised Feature Selection

2025-10-02 · Taurai Muvunza, Egor Kraev, Pere Planell-Morell, Alexander Y. Shestopaloff arxiv

Existing feature filters rely on statistical pair-wise dependence metrics to model feature-target relationships, but this approach may fail when the target depends on higher-order feature interactions rather than individ…

Representation LearningFeature Importance