Recurrence of optimum for training weight and activation quantized networks

DOI10.1016/J.ACHA.2022.07.006MaRDI QIDQ2105102zbMATH OpenOpenAlexFDO

Authors Ziang Long, Penghang Yin, Jack Xin

Publication date 8 December 2022

Published in Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2012.05529

zbMATH Keywords

neural networksquantizationdiscrete optimiztionstraight-through estimator

Mathematics Subject Classification ID

Computer science (68-XX) Operations research, mathematical programming (90-XX)

Recommendations

• Blended coarse gradient descent for full quantization of deep neural networks
• scientific article; zbMATH DE number 6982943
• BinaryRelax: a relaxation approach for training deep neural networks with quantized weights
• A greedy algorithm for quantizing neural networks
• Learning quantized neural nets by coarse gradient method for nonlinear classification

Cited in

(1)

• Post-training Quantization for Neural Networks with Provable Guarantees

Describes a project that uses

Uses Software

• XNOR-Net
• ImageNet
• CIFAR

This page was built for publication: Recurrence of optimum for training weight and activation quantized networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2105102)