# learn2learn: A Library for Meta-Learning Research

arXiv: https://arxiv.org/abs/2008.12284 · HTML: https://mlsanity.com/paper/2008.12284/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2020.

## Built on by (most cited first, 30 of 69)

- [A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum](https://mlsanity.com/paper/2102.07367/) (2021)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [FLEX: Unifying Evaluation for Few-Shot NLP](https://mlsanity.com/paper/2107.07170/) (2021)
- [Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation](https://mlsanity.com/paper/2106.09017/) (2021)
- [Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability](https://mlsanity.com/paper/2102.06589/) (2021)
- [Betty: An Automatic Differentiation Library for Multilevel Optimization](https://mlsanity.com/paper/2207.02849/) (2022)
- [Few-shot Learning with Noisy Labels](https://mlsanity.com/paper/2204.05494/) (2022)
- [Hypernetworks for Zero-shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/2211.15457/) (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)
- [On sensitivity of meta-learning to support data](https://mlsanity.com/paper/2110.13953/) (2021)
- [Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods](https://mlsanity.com/paper/2207.02829/) (2022)
- [Boosting Natural Language Generation from Instructions with Meta-Learning](https://mlsanity.com/paper/2210.11617/) (2022)
- [Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD](https://mlsanity.com/paper/2109.07497/) (2021)
- [Meta-Learning of Neural State-Space Models Using Data From Similar Systems](https://mlsanity.com/paper/2211.07768/) (2022)
- [X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answering](https://mlsanity.com/paper/2104.09696/) (2021)
- [Minimax and Neyman-Pearson Meta-Learning for Outlier Languages](https://mlsanity.com/paper/2106.01051/) (2021)
- [The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence](https://mlsanity.com/paper/2208.01545/) (2022)
- [Learning to Learn and Sample BRDFs](https://mlsanity.com/paper/2210.03510/) (2022)
- [Meta-Learning with Self-Improving Momentum Target](https://mlsanity.com/paper/2210.05185/) (2022)
- [Meta-learning in healthcare: A survey](https://mlsanity.com/paper/2308.02877/) (2023)
- [TIML: Task-Informed Meta-Learning for Agriculture](https://mlsanity.com/paper/2202.02124/) (2022)
- [Transductive Decoupled Variational Inference for Few-Shot Classification](https://mlsanity.com/paper/2208.10559/) (2022)
- [Task-Adaptive Meta-Learning Framework for Advancing Spatial Generalizability](https://mlsanity.com/paper/2212.06864/) (2022)
- [Metamizer: a versatile neural optimizer for fast and accurate physics simulations](https://mlsanity.com/paper/2410.19746/) (2024)
- [Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory](https://mlsanity.com/paper/2411.00401/) (2024)
- [Differentiable Model Predictive Control on the GPU](https://mlsanity.com/paper/2510.06179/) (2025)
- [A Channel Coding Benchmark for Meta-Learning](https://mlsanity.com/paper/2107.07579/) (2021)
- [Uniform Sampling over Episode Difficulty](https://mlsanity.com/paper/2108.01662/) (2021)
- [Is Pre-training Truly Better Than Meta-Learning?](https://mlsanity.com/paper/2306.13841/) (2023)

## Abstract (arXiv)

Meta-learning researchers face two fundamental issues in their empirical work: prototyping and reproducibility. Researchers are prone to make mistakes when prototyping new algorithms and tasks because modern meta-learning methods rely on unconventional functionalities of machine learning frameworks. In turn, reproducing existing results becomes a tedious endeavour -- a situation exacerbated by the lack of standardized implementations and benchmarks. As a result, researchers spend inordinate amounts of time on implementing software rather than understanding and developing new ideas. This manuscript introduces learn2learn, a library for meta-learning research focused on solving those prototyping and reproducibility issues. learn2learn provides low-level routines common across a wide-range of meta-learning techniques (e.g. meta-descent, meta-reinforcement learning, few-shot learning), and builds standardized interfaces to algorithms and benchmarks on top of them. In releasing learn2learn under a free and open source license, we hope to foster a community around standardized software for meta-learning research.