Generalized Inner Loop Meta-Learning

2019/10/03 by Edward Grefenstette, Brandon Amos, Grefenstette, Edward +15 · 1 citation
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.1910.01727

openalex publication_date 2019/10/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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, higher, 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.

Citations

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Stochastic Approximation Method
• Practical Bayesian Optimization of Machine Learning Algorithms
• RL²: Fast Reinforcement Learning via Slow Reinforcement Learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Meta-Learning with Latent Embedding Optimization

Cited by

• Tailoring: encoding inductive biases by optimizing unsupervised\n objectives at prediction time

Related

• A Tutorial on Meta-Reinforcement Learning
• Submodular Meta-Learning
• Meta-Learning in Neural Networks: A Survey
• Eliminating Meta Optimization Through Self-Referential Meta Learning
• Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees