# Generalized Inner Loop Meta-Learning

arXiv: https://arxiv.org/abs/1910.01727 · HTML: https://mlsanity.com/paper/1910.01727/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2019.

## Built on by (most cited first, 30 of 93)

- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [Offline Meta-Reinforcement Learning with Advantage Weighting](https://mlsanity.com/paper/2008.06043/) (2020)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [A Survey of Contextual Optimization Methods for Decision Making under Uncertainty](https://mlsanity.com/paper/2306.10374/) (2023)
- [Theseus: A Library for Differentiable Nonlinear Optimization](https://mlsanity.com/paper/2207.09442/) (2022)
- [A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization](https://mlsanity.com/paper/2106.07991/) (2021)
- [Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models](https://mlsanity.com/paper/2211.14946/) (2022)
- [Model-Based Inverse Reinforcement Learning from Visual Demonstrations](https://mlsanity.com/paper/2010.09034/) (2020)
- [Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies](https://mlsanity.com/paper/2112.13835/) (2021)
- [Meta-learning PINN loss functions](https://mlsanity.com/paper/2107.05544/) (2021)
- [Modeling rapid language learning by distilling Bayesian priors into artificial neural networks](https://mlsanity.com/paper/2305.14701/) (2023)
- [Betty: An Automatic Differentiation Library for Multilevel Optimization](https://mlsanity.com/paper/2207.02849/) (2022)
- [Gradient-based Bi-level Optimization for Deep Learning: A Survey](https://mlsanity.com/paper/2207.11719/) (2022)
- [Value-Function-based Sequential Minimization for Bi-level Optimization](https://mlsanity.com/paper/2110.04974/) (2021)
- [SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition](https://mlsanity.com/paper/2212.00724/) (2022)
- [Learning to Scaffold: Optimizing Model Explanations for Teaching](https://mlsanity.com/paper/2204.10810/) (2022)
- [TorchOpt: An Efficient Library for Differentiable Optimization](https://mlsanity.com/paper/2211.06934/) (2022)
- [Making Scalable Meta Learning Practical](https://mlsanity.com/paper/2310.05674/) (2023)
- [A Meta-Learning Approach for Training Explainable Graph Neural Networks](https://mlsanity.com/paper/2109.09426/) (2021)
- [On sensitivity of meta-learning to support data](https://mlsanity.com/paper/2110.13953/) (2021)
- [Boosting Natural Language Generation from Instructions with Meta-Learning](https://mlsanity.com/paper/2210.11617/) (2022)
- [Exploring Distributional Shifts in Large Language Models for Code Analysis](https://mlsanity.com/paper/2303.09128/) (2023)
- [Balanced softmax cross-entropy for incremental learning with and without memory](https://mlsanity.com/paper/2103.12532/) (2021)
- [TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation](https://mlsanity.com/paper/2502.02854/) (2025)
- [On the Influence of Masking Policies in Intermediate Pre-training](https://mlsanity.com/paper/2104.08840/) (2021)
- [Multimodality in Meta-Learning: A Comprehensive Survey](https://mlsanity.com/paper/2109.13576/) (2021)
- [Learning to Generate Synthetic Training Data using Gradient Matching and Implicit Differentiation](https://mlsanity.com/paper/2203.08559/) (2022)
- [Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?](https://mlsanity.com/paper/2302.08143/) (2023)
- [Recursive self-improvement of AI research agents](https://mlsanity.com/paper/2609.26457/) (2026)

## Abstract (arXiv)

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.