# Alpha MAML: Adaptive Model-Agnostic Meta-Learning

arXiv: https://arxiv.org/abs/1905.07435 · HTML: https://mlsanity.com/paper/1905.07435/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2019.

## Built on by (most cited first, 25 of 25)

- [Personalized Federated Learning using Hypernetworks](https://mlsanity.com/paper/2103.04628/) (2021)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Personalized Federated Learning with Gaussian Processes](https://mlsanity.com/paper/2106.15482/) (2021)
- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [Domain Invariant Representation Learning with Domain Density Transformations](https://mlsanity.com/paper/2102.05082/) (2021)
- [Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning](https://mlsanity.com/paper/2110.03909/) (2021)
- [An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning](https://mlsanity.com/paper/2308.00788/) (2023)
- [Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks](https://mlsanity.com/paper/2102.03832/) (2021)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Learning to Learn from APIs: Black-Box Data-Free Meta-Learning](https://mlsanity.com/paper/2305.18413/) (2023)
- [PAC-Bayes Bounds for Meta-learning with Data-Dependent Prior](https://mlsanity.com/paper/2102.03748/) (2021)
- [Task Discovery: Finding the Tasks that Neural Networks Generalize on](https://mlsanity.com/paper/2212.00261/) (2022)
- [A Partially Supervised Reinforcement Learning Framework for Visual Active Search](https://mlsanity.com/paper/2310.09689/) (2023)
- [Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning](https://mlsanity.com/paper/2106.04911/) (2021)
- [Convergence of Gradient-based MAML in LQR](https://mlsanity.com/paper/2309.06588/) (2023)
- [Embedding Adaptation is Still Needed for Few-Shot Learning](https://mlsanity.com/paper/2104.07255/) (2021)
- [Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalization](https://mlsanity.com/paper/2108.00785/) (2021)
- [Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworks](https://mlsanity.com/paper/2307.06771/) (2023)
- [Meta Adversarial Perturbations](https://mlsanity.com/paper/2111.10291/) (2021)
- [Towards Personalized Preprocessing Pipeline Search](https://mlsanity.com/paper/2302.14329/) (2023)
- [Meta-Learning Neural Procedural Biases](https://mlsanity.com/paper/2406.07983/) (2024)
- [Benchmarking for Practice: Few-Shot Time-Series Crop-Type Classification on the EuroCropsML Dataset](https://mlsanity.com/paper/2504.11022/) (2025)
- [Heterogeneity-Oblivious Robust Federated Learning](https://mlsanity.com/paper/2508.03579/) (2025)
- [Graceful Degradation and Related Fields](https://mlsanity.com/paper/2106.11119/) (2021)
- [Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent](https://mlsanity.com/paper/2602.19837/) (2026)

## Abstract (arXiv)

Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks. The MAML algorithm performs well on few-shot learning problems in classification, regression, and fine-tuning of policy gradients in reinforcement learning, but comes with the need for costly hyperparameter tuning for training stability. We address this shortcoming by introducing an extension to MAML, called Alpha MAML, to incorporate an online hyperparameter adaptation scheme that eliminates the need to tune meta-learning and learning rates. Our results with the Omniglot database demonstrate a substantial reduction in the need to tune MAML training hyperparameters and improvement to training stability with less sensitivity to hyperparameter choice.