Saved in:
Bibliographic Details
Main Author: Biswas, Aditya
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.19112
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911859670515712
author Biswas, Aditya
author_facet Biswas, Aditya
contents We present PSiLON Net, an MLP architecture that uses $L_1$ weight normalization for each weight vector and shares the length parameter across the layer. The 1-path-norm provides a bound for the Lipschitz constant of a neural network and reflects on its generalizability, and we show how PSiLON Net's design drastically simplifies the 1-path-norm, while providing an inductive bias towards efficient learning and near-sparse parameters. We propose a pruning method to achieve exact sparsity in the final stages of training, if desired. To exploit the inductive bias of residual networks, we present a simplified residual block, leveraging concatenated ReLU activations. For networks constructed with such blocks, we prove that considering only a subset of possible paths in the 1-path-norm is sufficient to bound the Lipschitz constant. Using the 1-path-norm and this improved bound as regularizers, we conduct experiments in the small data regime using overparameterized PSiLON Nets and PSiLON ResNets, demonstrating reliable optimization and strong performance.
format Preprint
id arxiv_https___arxiv_org_abs_2404_19112
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hidden Synergy: $L_1$ Weight Normalization and 1-Path-Norm Regularization
Biswas, Aditya
Machine Learning
We present PSiLON Net, an MLP architecture that uses $L_1$ weight normalization for each weight vector and shares the length parameter across the layer. The 1-path-norm provides a bound for the Lipschitz constant of a neural network and reflects on its generalizability, and we show how PSiLON Net's design drastically simplifies the 1-path-norm, while providing an inductive bias towards efficient learning and near-sparse parameters. We propose a pruning method to achieve exact sparsity in the final stages of training, if desired. To exploit the inductive bias of residual networks, we present a simplified residual block, leveraging concatenated ReLU activations. For networks constructed with such blocks, we prove that considering only a subset of possible paths in the 1-path-norm is sufficient to bound the Lipschitz constant. Using the 1-path-norm and this improved bound as regularizers, we conduct experiments in the small data regime using overparameterized PSiLON Nets and PSiLON ResNets, demonstrating reliable optimization and strong performance.
title Hidden Synergy: $L_1$ Weight Normalization and 1-Path-Norm Regularization
topic Machine Learning
url https://arxiv.org/abs/2404.19112