Back to Search
Start Over
Decoupled Weight Decay for Any $p$ Norm
- Publication Year :
- 2024
-
Abstract
- With the success of deep neural networks (NNs) in a variety of domains, the computational and storage requirements for training and deploying large NNs have become a bottleneck for further improvements. Sparsification has consequently emerged as a leading approach to tackle these issues. In this work, we consider a simple yet effective approach to sparsification, based on the Bridge, or $L_p$ regularization during training. We introduce a novel weight decay scheme, which generalizes the standard $L_2$ weight decay to any $p$ norm. We show that this scheme is compatible with adaptive optimizers, and avoids the gradient divergence associated with $0<p<1$ norms. We empirically demonstrate that it leads to highly sparse networks, while maintaining generalization performance comparable to standard $L_2$ regularization.<br />Comment: GitHub link: https://github.com/Nadav-out/PAdam
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2404.10824
- Document Type :
- Working Paper