Back to Search Start Over

Unifying back-propagation and forward-forward algorithms through model predictive control

Unifying back-propagation and forward-forward algorithms through model predictive control

Authors :
Ren, Lianhai
Li, Qianxiao
Publication Year :
2024

Abstract

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.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2409.19561
Document Type :
Working Paper