Binary quantized network training with sharpness-aware minimization

DOI10.1007/S10915-022-02064-7OpenAlexW4311036102MaRDI QIDQ2111176FDOQ2111176

Authors Ren Liu, Fengmiao Bian, Xiaoqun Zhang

Publication date 23 December 2022

Published in Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10915-022-02064-7

zbMATH Keywords

binary quantized networksharpness-aware minimization

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Artificial neural networks and deep learning (68T07)

Recommendations

• Post-training Quantization for Neural Networks with Provable Guarantees
• Stochastic Markov gradient descent and training low-bit neural networks
• BinaryRelax: a relaxation approach for training deep neural networks with quantized weights
• Learning quantized neural nets by coarse gradient method for nonlinear classification
• Blended coarse gradient descent for full quantization of deep neural networks

Cites work

• scientific article; zbMATH DE number 6982943 (Why is no real title available?)
• BinaryRelax: a relaxation approach for training deep neural networks with quantized weights
• Convergence of stochastic proximal gradient algorithm
• Multilayer feedforward neural networks with single powers-of-two weights

Cited in

(4)

• Post-training Quantization for Neural Networks with Provable Guarantees
• Training neural networks from an ergodic perspective
• Stochastic quantization for learning accurate low-bit deep neural networks
• scientific article; zbMATH DE number 6982943 (Why is no real title available?)

Describes a project that uses

Uses Software

• CIFAR
• ImageNet
• AlexNet
• GPipe
• EfficientNet
• XNOR-Net
• Faster R-CNN

This page was built for publication: Binary quantized network training with sharpness-aware minimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2111176)