Towards compact neural networks via end-to-end training: a Bayesian tensor approach with automatic rank determination

DOI10.1137/21M1391444OpenAlexW3118185732MaRDI QIDQ5037563FDOQ5037563

Authors Cole Hawkins, Xing Liu, Zheng Zhang 

Publication date 1 March 2022

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2010.08689

zbMATH Keywords

low-rank tensorcompact neural networkscompressed trainingtensor rank determination

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Hybrid tensor decomposition in neural network compression
• CMD: controllable matrix decomposition with global optimization for deep neural network compression
• Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 2 Applications and Future Perspectives
• Multiresolution low-rank tensor formats
• Tensor networks for dimensionality reduction and large-scale optimization. I: Low-rank tensor decompositions

Cites Work

• scientific article; zbMATH DE number 6377992 (Why is no real title available?)
• scientific article; zbMATH DE number 6982943 (Why is no real title available?)
• An introduction to variational methods for graphical models
• Analysis of individual differences in multidimensional scaling via an \(n\)-way generalization of ``Eckart-Young decomposition
• Bayesian tensor regression
• Mean field variational Bayes for elaborate distributions
• Model selection in Bayesian neural networks via horseshoe priors
• PARAFAC: Parallel factor analysis
• Robust low-rank tensor recovery: models and algorithms
• Tensor Decompositions and Applications
• Tensor Regression with Applications in Neuroimaging Data Analysis
• Tensor completion and low-\(n\)-rank tensor recovery via convex optimization
• Tensor-train decomposition
• The horseshoe estimator for sparse signals

Cited In (2)

• CMD: controllable matrix decomposition with global optimization for deep neural network compression
• Hybrid tensor decomposition in neural network compression

Uses Software

• PARAFAC
• TensorLy
• GitHub
• BinaryNet
• MUSCO

This page was built for publication: Towards compact neural networks via end-to-end training: a Bayesian tensor approach with automatic rank determination

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5037563)