Diffeomorphic information neural estimation
Abstract Mutual Information (MI) and Conditional Mutual Information (CMI) are multi-purpose
tools from information theory that are able to naturally measure the statistical dependencies …
tools from information theory that are able to naturally measure the statistical dependencies …
Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax
I Butakov, A Sememenko, A Tolmachev… - arXiv preprint arXiv …, 2024 - arxiv.org
Deep InfoMax (DIM) is a well-established method for self-supervised representation learning
(SSRL) based on maximization of the mutual information between the input and the output of …
(SSRL) based on maximization of the mutual information between the input and the output of …
Enabling Causal Discovery in Post-Nonlinear Models with Normalizing Flows
Post-nonlinear (PNL) causal models stand out as a versatile and adaptable framework for
modeling intricate causal relationships. However, accurately capturing the invertibility …
modeling intricate causal relationships. However, accurately capturing the invertibility …