Sparse loss-aware ternarization for neural networks

DOI10.1016/J.INS.2024.121668MaRDI QIDQ6665140zbMATH OpenFDO

Authors Ruizhi Zhou, Lingfeng Niu, Dachuan Xu

Publication date 16 January 2025

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.INS.2024.121668

zbMATH Keywords

ADMMloss-aware quantizationmachine learningsparse regularizationternary neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites work

• A dual algorithm for the solution of nonlinear variational problems via finite element approximation
• A simple effective heuristic for embedded mixed-integer quadratic programming
• BinaryRelax: a relaxation approach for training deep neural networks with quantized weights
• Convergence analysis of alternating direction method of multipliers for a family of nonconvex problems
• Deep learning
• Distributed optimization and statistical learning via the alternating direction method of multipliers
• Douglas--Rachford Splitting and ADMM for Nonconvex Optimization: Tight Convergence Results
• Global convergence of ADMM in nonconvex nonsmooth optimization
• scientific article; zbMATH DE number 7626714 (Why is no real title available?)
• Sparsity-control ternary weight networks

This page was built for publication: Sparse loss-aware ternarization for neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6665140)