DeepAI AI Chat
Log In Sign Up

On the Global Optimality of Model-Agnostic Meta-Learning

by   Lingxiao Wang, et al.

Model-agnostic meta-learning (MAML) formulates meta-learning as a bilevel optimization problem, where the inner level solves each subtask based on a shared prior, while the outer level searches for the optimal shared prior by optimizing its aggregated performance over all the subtasks. Despite its empirical success, MAML remains less understood in theory, especially in terms of its global optimality, due to the nonconvexity of the meta-objective (the outer-level objective). To bridge such a gap between theory and practice, we characterize the optimality gap of the stationary points attained by MAML for both reinforcement learning and supervised learning, where the inner-level and outer-level problems are solved via first-order optimization methods. In particular, our characterization connects the optimality gap of such stationary points with (i) the functional geometry of inner-level objectives and (ii) the representation power of function approximators, including linear models and neural networks. To the best of our knowledge, our analysis establishes the global optimality of MAML with nonconvex meta-objectives for the first time.


page 1

page 2

page 3

page 4


A Bridge Between Hyperparameter Optimization and Larning-to-learn

We consider a class of a nested optimization problems involving inner an...

Meta-Learning with Neural Tangent Kernels

Model Agnostic Meta-Learning (MAML) has emerged as a standard framework ...

On Implicit Bias in Overparameterized Bilevel Optimization

Many problems in machine learning involve bilevel optimization (BLO), in...

UFO-BLO: Unbiased First-Order Bilevel Optimization

Bilevel optimization (BLO) is a popular approach with many applications ...

Model agnostic methods meta-learn despite misspecifications

Due to its empirical success on few shot classification and reinforcemen...

On Stability and Generalization of Bilevel Optimization Problem

(Stochastic) bilevel optimization is a frequently encountered problem in...

On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms

In this paper, we study the convergence theory of a class of gradient-ba...