Unifying Back-Propagation and Forward-Forward Algorithms through Model Predictive Control

19 Sept 2024 (modified: 18 Nov 2024)ICLR 2025 Conference Withdrawn SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: deep learning optimization, model predictive control
TL;DR: We present a novel MPC framework for deep learning, unifying BP and Forward-Forward techniques. We analyze accuracy and memory trade-offs and validate a horizon selection algorithm with theoretical and experimental support.
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.

Supplementary Material: zip
Primary Area: optimization
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 1739
Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview