Random pruning over-parameterized neural networks can improve generalization: a training dynamics analysis

MaRDI QIDQ6947045zbMATH OpenFDO

Authors Hongru Yang, Yingbin Liang, Xiaojie Guo, Lingfei Wu, Zhangyang Wang

Publication date 5 August 2025

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/23-0832.html

zbMATH Keywords

neural networkpruning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites work

• A mean field view of the landscape of two-layer neural networks
• A topological insight into restricted Boltzmann machines
• Feature purification: how adversarial training performs robust deep learning
• Gradient descent optimizes over-parameterized deep ReLU networks
• Mean field analysis of neural networks: a law of large numbers

This page was built for publication: Random pruning over-parameterized neural networks can improve generalization: a training dynamics analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6947045)