Optimal Protocols for Continual Learning via Statistical Physics and Control Theory

Artificial neural networks often struggle with catastrophic forgetting when learning multiple tasks sequentially, as training on new tasks degrades performance on previously learned tasks. Recent theoretical work has addressed this issue by analysing learning curves in synthetic frameworks under predefined * This article is an updated version of a paper presented at the ICLR 2025 conference (Mori F, Mannelli S S, and Mignacco F 2025 Optimal protocols for continual learning via statistical physics and control theory 13th Int. Conf. on Learning Representations (available at: https://openreview.net/forum?id=rhhQjGj09A )).