# Meta Continual Learning via Dynamic Programming

arXiv: https://arxiv.org/abs/2008.02219 · HTML: https://mlsanity.com/paper/2008.02219/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2020.

## Built on by (most cited first, 4 of 4)

- [AugFL: Augmenting Federated Learning with Pretrained Models](https://mlsanity.com/paper/2503.02154/) (2025)
- [Parabolic Continual Learning](https://mlsanity.com/paper/2503.02117/) (2025)
- [ATLAS: Universal Function Approximator for Memory Retention](https://mlsanity.com/paper/2208.05388/) (2022)
- [Learning Continually on a Sequence of Graphs -- The Dynamical System Way](https://mlsanity.com/paper/2305.12030/) (2023)

## Abstract (arXiv)

Meta continual learning algorithms seek to train a model when faced with similar tasks observed in a sequential manner. Despite promising methodological advancements, there is a lack of theoretical frameworks that enable analysis of learning challenges such as generalization and catastrophic forgetting. To that end, we develop a new theoretical approach for meta continual learning~(MCL) where we mathematically model the learning dynamics using dynamic programming, and we establish conditions of optimality for the MCL problem. Moreover, using the theoretical framework, we derive a new dynamic-programming-based MCL method that adopts stochastic-gradient-driven alternating optimization to balance generalization and catastrophic forgetting. We show that, on MCL benchmark data sets, our theoretically grounded method achieves accuracy better than or comparable to that of existing state-of-the-art methods.