Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Venkatasubramanian, Shyam, Aloui, Ahmed, Tarokh, Vahid
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914816805830656
author Venkatasubramanian, Shyam
Aloui, Ahmed
Tarokh, Vahid
author_facet Venkatasubramanian, Shyam
Aloui, Ahmed
Tarokh, Vahid
contents Advancing loss function design is pivotal for optimizing neural network training and performance. This work introduces Random Linear Projections (RLP) loss, a novel approach that enhances training efficiency by leveraging geometric relationships within the data. Distinct from traditional loss functions that target minimizing pointwise errors, RLP loss operates by minimizing the distance between sets of hyperplanes connecting fixed-size subsets of feature-prediction pairs and feature-label pairs. Our empirical evaluations, conducted across benchmark datasets and synthetic examples, demonstrate that neural networks trained with RLP loss outperform those trained with traditional loss functions, achieving improved performance with fewer data samples, and exhibiting greater robustness to additive noise. We provide theoretical analysis supporting our empirical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2311_12356
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks
Venkatasubramanian, Shyam
Aloui, Ahmed
Tarokh, Vahid
Machine Learning
Advancing loss function design is pivotal for optimizing neural network training and performance. This work introduces Random Linear Projections (RLP) loss, a novel approach that enhances training efficiency by leveraging geometric relationships within the data. Distinct from traditional loss functions that target minimizing pointwise errors, RLP loss operates by minimizing the distance between sets of hyperplanes connecting fixed-size subsets of feature-prediction pairs and feature-label pairs. Our empirical evaluations, conducted across benchmark datasets and synthetic examples, demonstrate that neural networks trained with RLP loss outperform those trained with traditional loss functions, achieving improved performance with fewer data samples, and exhibiting greater robustness to additive noise. We provide theoretical analysis supporting our empirical findings.
title Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2311.12356