Generalized Inner Loop Meta-Learning
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.
Code (3)
Tasks
Meta-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
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 parameters over both the inner loop of task-specific…
Meta-LearningMeta-Learning with Implicit Gradients
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 an effective approach for few-shot…
Few-Shot Image ClassificationFew-Shot LearningMeta-LearningCooperative Meta-Learning with Gradient Augmentation
Model agnostic meta-learning (MAML) is one of the most widely used gradient-based meta-learning, consisting of two optimization loops: an inner loop and outer loop. MAML learns the new task from meta-initialization param…
Few-Shot Image Classificationimage-classificationImage ClassificationMeta-Learning+1Bilevel Autoresearch: Meta-Autoresearching Itself
If autoresearch is itself a form of research, then autoresearch can be applied to research itself. We present Bilevel Autoresearch, a bilevel framework in which an outer autoresearch loop improves an inner autoresearch l…
Multi-Armed BanditsDo What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks
While artificial neural networks (ANNs) have been widely adopted in machine learning, researchers are increasingly obsessed by the gaps between ANNs and natural neural networks (NNNs). In this paper, we propose a framewo…
Meta-Learning