How to train your MAML
read the original 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++.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
The Statistical Cost of Adaptation in Multi-Source Transfer Learning
Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
-
ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting
ForeSplat introduces MetaGrad, a meta-gradient training rule that equips feed-forward 3DGS models to produce initializations optimized for rapid downstream refinement, improving convergence speed and final quality ove...
-
ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting
ForeSplat introduces MetaGrad, a meta-gradient training rule that makes feed-forward 3DGS predictions optimization-aware so they converge faster and to higher quality upon refinement.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.