Gradient-based meta-learning and hyperparameter optimization have seen significant
progress recently, enabling practical end-to-end training of neural networks together with …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Gradient-based meta-learning methods leverage gradient descent to learn the
commonalities among various tasks. While previous such methods have been successful in …

Although model-agnostic meta-learning (MAML) is a very successful algorithm in meta-
learning practice, it can have high computational cost because it updates all model …

Deep learning based natural language processing (NLP) has become the mainstream of
research in recent years and significantly outperforms conventional methods. However …

We develop a functional encoder-decoder approach to supervised meta-learning, where
labeled data is encoded into an infinite-dimensional functional representation rather than a …

With the growing attention on learning-to-learn new tasks using only a few examples, meta-
learning has been widely used in numerous problems such as few-shot classification …

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 …

Meta-learning aims to use the knowledge from previous tasks to facilitate the learning of
novel tasks. Many meta-learning models elaborately design various task-shared inductive …

Recent years have witnessed an abundance of new publications and approaches on meta-
learning. This community-wide enthusiasm has sparked great insights but has also created …