Unifying back-propagation and forward-forward algorithms through model predictive control
Machine Learning
2024-10-01 v1 Optimization and Control
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.
Cite
@article{arxiv.2409.19561,
title = {Unifying back-propagation and forward-forward algorithms through model predictive control},
author = {Lianhai Ren and Qianxiao Li},
journal= {arXiv preprint arXiv:2409.19561},
year = {2024}
}