Deep neural network compression via data-driven low-rank singular value decomposition

DOI10.1613/JAIR.1.18694MaRDI QIDQ7307211zbMATH OpenFDO

Authors Abdelfattah Toulaoui, Hamza Khalfi, I. Hafidi

Publication date 31 July 2026

Published in The Journal of Artificial Intelligence Research (JAIR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1613/JAIR.1.18694

Mathematics Subject Classification ID

Vector spaces, linear dependence, rank, lineability (15A03) Artificial neural networks and deep learning (68T07)

Cites work

• Eigenvalue distribution of large random matrices arising in deep neural networks: Orthogonal case
• scientific article; zbMATH DE number 6982943 (Why is no real title available?)
• scientific article; zbMATH DE number 7415108 (Why is no real title available?)
• scientific article; zbMATH DE number 961607 (Why is no real title available?)
• Loss aware post-training quantization
• On the Early History of the Singular Value Decomposition
• On Updating Problems in Latent Semantic Indexing
• Optimizing sparse matrix-matrix multiplication for the GPU
• Statistical comparisons of classifiers over multiple data sets
• SVD-based incremental approaches for recommender systems

This page was built for publication: Deep neural network compression via data-driven low-rank singular value decomposition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7307211)