Recasting Gradient-Based Meta-Learning as Hierarchical Bayes

Understand

Meta-learning allows an intelligent agent to leverage prior learning episodes as a basis for quickly improving performance on a novel task.

• Bayesian hierarchical modeling provides a theoretical framework for formalizing meta-learning as inference for a set of parameters that are shared across tasks.
• Here, we reformulate the model-agnostic meta-learning algorithm (MAML) of Finn et al.
• (2017) as a method for probabilistic inference in a hierarchical Bayesian model.