@article{antoniou_how_2018, title = {How to train your {MAML}}, url = {http://arxiv.org/abs/1810.09502}, abstract = {The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic Meta Learning or {MAML} is currently one of the best approaches for few-shot learning via meta-learning. {MAML} is simple, elegant and very powerful, however, it has a variety of issues, such as being very sensitive to neural network architectures, often leading to instability during training, requiring arduous hyperparameter searches to stabilize training and achieve high generalization and being very computationally expensive at both training and inference times. In this paper, we propose various modifications to {MAML} that not only stabilize the system, but also substantially improve the generalization performance, convergence speed and computational overhead of {MAML}, which we call {MAML}++.}, journaltitle = {{arXiv}:1810.09502 [cs, stat]}, author = {Antoniou, Antreas and Edwards, Harrison and Storkey, Amos}, urldate = {2019-07-01}, date = {2018-10-22}, eprinttype = {arxiv}, eprint = {1810.09502}, keywords = {Computer Science - Machine Learning, Statistics - Machine Learning}, }