English

Meta Learning in the Continuous Time Limit

Machine Learning 2020-07-09 v2 Machine Learning

Abstract

In this paper, we establish the ordinary differential equation (ODE) that underlies the training dynamics of Model-Agnostic Meta-Learning (MAML). Our continuous-time limit view of the process eliminates the influence of the manually chosen step size of gradient descent and includes the existing gradient descent training algorithm as a special case that results from a specific discretization. We show that the MAML ODE enjoys a linear convergence rate to an approximate stationary point of the MAML loss function for strongly convex task losses, even when the corresponding MAML loss is non-convex. Moreover, through the analysis of the MAML ODE, we propose a new BI-MAML training algorithm that significantly reduces the computational burden associated with existing MAML training methods. To complement our theoretical findings, we perform empirical experiments to showcase the superiority of our proposed methods with respect to the existing work.

Keywords

Cite

@article{arxiv.2006.10921,
  title  = {Meta Learning in the Continuous Time Limit},
  author = {Ruitu Xu and Lin Chen and Amin Karbasi},
  journal= {arXiv preprint arXiv:2006.10921},
  year   = {2020}
}

Comments

25 pages

R2 v1 2026-06-23T16:27:13.943Z