Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Malanchuk, Sofia"'
We propose a novel approach to the problem of mutual information (MI) estimation via introducing a family of estimators based on normalizing flows. The estimator maps original data to the target distribution, for which MI is easier to estimate. We ad
Externí odkaz:
http://arxiv.org/abs/2403.02187
Autor:
Butakov, Ivan, Tolmachev, Alexander, Malanchuk, Sofia, Neopryatnaya, Anna, Frolov, Alexey, Andreev, Kirill
The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs). Its essence lies in tracking the dynamics of two mutual information (MI) values: between the hidden
Externí odkaz:
http://arxiv.org/abs/2305.08013