Saved in:
Bibliographic Details
Main Authors: Ren, Lianhai, Li, Qianxiao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.19561
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916414332338176
author Ren, Lianhai
Li, Qianxiao
author_facet Ren, Lianhai
Li, Qianxiao
contents We introduce a Model Predictive Control (MPC) framework for training deep neural networks, systematically unifying the Back-Propagation (BP) and Forward-Forward (FF) algorithms. At the same time, it gives rise to a range of intermediate training algorithms with varying look-forward horizons, leading to a performance-efficiency trade-off. We perform a precise analysis of this trade-off on a deep linear network, where the qualitative conclusions carry over to general networks. Based on our analysis, we propose a principled method to choose the optimization horizon based on given objectives and model specifications. Numerical results on various models and tasks demonstrate the versatility of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19561
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unifying back-propagation and forward-forward algorithms through model predictive control
Ren, Lianhai
Li, Qianxiao
Machine Learning
Optimization and Control
We introduce a Model Predictive Control (MPC) framework for training deep neural networks, systematically unifying the Back-Propagation (BP) and Forward-Forward (FF) algorithms. At the same time, it gives rise to a range of intermediate training algorithms with varying look-forward horizons, leading to a performance-efficiency trade-off. We perform a precise analysis of this trade-off on a deep linear network, where the qualitative conclusions carry over to general networks. Based on our analysis, we propose a principled method to choose the optimization horizon based on given objectives and model specifications. Numerical results on various models and tasks demonstrate the versatility of our method.
title Unifying back-propagation and forward-forward algorithms through model predictive control
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2409.19561