Online Constrained Meta-Learning: Provable Guarantees for Generalization

Meta-learning has attracted attention due to its strong ability to learn experiences from known tasks, which can speed up and enhance the learning process for new tasks. However, most existing meta-learning approaches only can learn from tasks without any constraint. This paper proposes an online constrained meta-learning framework, which continuously learns meta-knowledge from sequential learning tasks, and the learning tasks are subject to hard constraints. Beyond existing meta-learning analyses, we provide the upper bounds of optimality gaps and constraint violations of the deployed task-specific models produced by the proposed framework. These metrics consider both the dynamic regret of online learning and the generalization ability of the task-specific models to unseen data. Moreover, we provide a practical algorithm for the framework and validate its superior effectiveness through experiments conducted on meta-imitation learning and few-shot image classification.