Gradient-based hyperparameter optimization has earned a widespread popularity in the
context of few-shot meta-learning, but remains broadly impractical for tasks with long …

Gradient-based meta-learning has earned a widespread popularity in few-shot learning, but
remains broadly impractical for tasks with long horizons (many gradient steps), due to …

A core capability of intelligent systems is the ability to quickly learn new tasks by drawing on
prior experience. Gradient (or optimization) based meta-learning has recently emerged as …

Few-shot meta-learning presents a challenge for gradient descent optimization due to the
limited number of training samples per task. To address this issue, we propose an episodic …

Meta-learning methods typically follow a two-loop framework, where each loop potentially
suffers from notorious overfitting, hindering rapid adaptation and generalization to new …

Optimization-based meta-learning algorithms are a powerful class of methods for learning-to-
learn applications such as few-shot learning. They tackle the limited availability of training …

In this paper, we hypothesize that gradient-based meta-learning (GBML) implicitly
suppresses the Hessian along the optimization trajectory in the inner loop. Based on this …

Abstract Model-agnostic meta learning (MAML) is currently one of the dominating
approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML …

Meta-learning of shared initialization parameters has shown to be highly effective in solving
few-shot learning tasks. However, extending the framework to many-shot scenarios, which …

Abstract We introduce Meta-AdaM, a meta-learned adaptive optimizer with momentum,
designed for few-shot learning tasks that pose significant challenges to deep learning …