Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis

Part of Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

Bibtex Paper Reviews And Public Comment » Supplemental

Authors

Qi CHEN, Changjian Shui, Mario Marchand

Abstract

We derive a novel information-theoretic analysis of the generalization property of meta-learning algorithms. Concretely, our analysis proposes a generic understanding in both the conventional learning-to-learn framework \citep{amit2018meta} and the modern model-agnostic meta-learning (MAML) algorithms \citep{finn2017model}.Moreover, we provide a data-dependent generalization bound for the stochastic variant of MAML, which is \emph{non-vacuous} for deep few-shot learning. As compared to previous bounds that depend on the square norms of gradients, empirical validations on both simulated data and a well-known few-shot benchmark show that our bound is orders of magnitude tighter in most conditions.