Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Evaluation of Forward-Only Algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Spyra, Przemysław, Dzwinel, Witold
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911246861729792
author Spyra, Przemysław
Dzwinel, Witold
author_facet Spyra, Przemysław
Dzwinel, Witold
contents The long-held assumption that backpropagation (BP) is essential for state-of-the-art performance is challenged by this work. We present rigorous, hardware-validated evidence that the Mono-Forward (MF) algorithm, a backpropagation-free method, consistently surpasses an optimally tuned BP baseline in classification accuracy on its native Multi-Layer Perceptron (MLP) architectures. This superior generalization is achieved with profound efficiency gains, including up to 41% less energy consumption and up to 34% faster training. Our analysis, which charts an evolutionary path from Geoffrey Hinton's Forward-Forward (FF) to the Cascaded Forward (CaFo) and finally to MF, is grounded in a fair comparative framework using identical architectures and universal hyperparameter optimization. We further provide a critical re-evaluation of memory efficiency in BP-free methods, empirically demonstrating that practical overhead can offset theoretical gains. Ultimately, this work establishes MF as a practical, high-performance, and sustainable alternative to BP for MLPs.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01061
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Evaluation of Forward-Only Algorithms
Spyra, Przemysław
Dzwinel, Witold
Machine Learning
Artificial Intelligence
68T07
I.2.0
The long-held assumption that backpropagation (BP) is essential for state-of-the-art performance is challenged by this work. We present rigorous, hardware-validated evidence that the Mono-Forward (MF) algorithm, a backpropagation-free method, consistently surpasses an optimally tuned BP baseline in classification accuracy on its native Multi-Layer Perceptron (MLP) architectures. This superior generalization is achieved with profound efficiency gains, including up to 41% less energy consumption and up to 34% faster training. Our analysis, which charts an evolutionary path from Geoffrey Hinton's Forward-Forward (FF) to the Cascaded Forward (CaFo) and finally to MF, is grounded in a fair comparative framework using identical architectures and universal hyperparameter optimization. We further provide a critical re-evaluation of memory efficiency in BP-free methods, empirically demonstrating that practical overhead can offset theoretical gains. Ultimately, this work establishes MF as a practical, high-performance, and sustainable alternative to BP for MLPs.
title Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Evaluation of Forward-Only Algorithms
topic Machine Learning
Artificial Intelligence
68T07
I.2.0
url https://arxiv.org/abs/2511.01061