Generalized Inner Loop Meta-Learning

Edward Grefenstette, Brandon Amos, Denis Yarats, Phu Mon Htut, Artem Molchanov, Franziska Meier, Douwe Kiela, Kyunghyun Cho, Soumith Chintala

Keywords: meta-learning

TL;DR: Lots of meta-learning problems follow the same general pattern, so we formalized it, proved stuff about it, turned it into an algorithm, and subsequently a pytorch library.

Abstract: Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimization problem. In this paper, we give a formalization of this shared pattern, which we call GIMLI, prove its general requirements, and derive a general-purpose algorithm for implementing similar approaches. Based on this analysis and algorithm, we describe a library of our design, unnamedlib, which we share with the community to assist and enable future research into these kinds of meta-learning approaches. We end the paper by showcasing the practical applications of this framework and library through illustrative experiments and ablation studies which they facilitate.

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:1910.01727/code)