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.
翻译:在面临相继观察到的类似任务时,元持续学习算法试图培训一个模式。尽管方法进展大有希望,但缺乏能够分析学习挑战的理论框架,例如一般化和灾难性遗忘。为此,我们为元持续学习制定了一个新的理论方法(MCL),我们用动态编程进行数学模型学习动态,并为MCL问题建立了最佳性条件。此外,我们利用理论框架,产生了一种新的动态-方案化MCL方法,采用随机分级驱动的交替优化,以平衡一般化和灾难性遗忘。我们在MCL基准数据集中显示,我们基于理论的方法的准确性优于或比现有最新方法的准确性。