# Wormhole MAML: Meta-Learning in Glued Parameter Space

arXiv: https://arxiv.org/abs/2212.14094 · HTML: https://mlsanity.com/paper/2212.14094/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 28 Dec 2022.

## Builds on (most cited first, 9 of 9)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [Why gradient clipping accelerates training: A theoretical justification for adaptivity](https://mlsanity.com/paper/1905.11881/) (2019)
- [Meta-Learning with Warped Gradient Descent](https://mlsanity.com/paper/1909.00025/) (2019)
- [Meta-Learning Requires Meta-Augmentation](https://mlsanity.com/paper/2007.05549/) (2020)

## Abstract (arXiv)

In this paper, we introduce a novel variation of model-agnostic meta-learning, where an extra multiplicative parameter is introduced in the inner-loop adaptation. Our variation creates a shortcut in the parameter space for the inner-loop adaptation and increases model expressivity in a highly controllable manner. We show both theoretically and numerically that our variation alleviates the problem of conflicting gradients and improves training dynamics. We conduct experiments on 3 distinctive problems, including a toy classification problem for threshold comparison, a regression problem for wavelet transform, and a classification problem on MNIST. We also discuss ways to generalize our method to a broader class of problems.