Linearly scalable learning of smooth low-dimensional patterns with permutation-aided entropic dimension reduction

DOI10.2140/CAMCOS.2024.19.87MaRDI QIDQ6644161zbMATH OpenFDO

Authors Illia Horenko, Lukáš Pospíšil

Publication date 27 November 2024

Published in Communications in Applied Mathematics and Computational Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.2140/CAMCOS.2024.19.87

zbMATH Keywords

entropypermutationregularizationunsupervised learningeconomical data

Mathematics Subject Classification ID

Computational learning theory (68Q32) Artificial intelligence (68T99) General topics in artificial intelligence (68T01)

Cites work

• scientific article; zbMATH DE number 3705907 (Why is no real title available?)
• scientific article; zbMATH DE number 3078983 (Why is no real title available?)
• scientific article; zbMATH DE number 3095897 (Why is no real title available?)
• Fuzzy spectral clustering by PCCA+: application to Markov state models and data classification
• Identification of almost invariant aggregates in reversible nearly uncoupled Markov chains
• Introduction to algorithms
• Lectures on Polytopes
• Metastability and Markov state models in molecular dynamics. Modeling, analysis, algorithmic approaches
• On Markov state models for metastable processes
• On a scalable entropic breaching of the overfitting barrier for small data problems in machine learning
• On convex relaxation of graph isomorphism
• Tikhonov regularization and the L-curve for large discrete ill-posed problems
• eSPA+: Scalable Entropy-Optimal Machine Learning Classification for Small Data Problems

This page was built for publication: Linearly scalable learning of smooth low-dimensional patterns with permutation-aided entropic dimension reduction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6644161)