Meta Learning in the Continuous Time Limit

Ruitu Xu · Lin Chen · Amin Karbasi

Keywords: [ Learning Theory and Statistics ] [ Other Theory / Statistics ]


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 reduces the computational burden associated with existing MAML training methods, and empirical experiments are performed to showcase the superiority of our proposed methods in the rate of convergence with respect to the vanilla MAML algorithm.

Chat is not available.