A New First-Order Meta-Learning Algorithm with Convergence Guarantees
Learning new tasks by drawing on prior experience gathered from other (related) tasks is a core property of any intelligent system. Gradient-based meta-learning, especially MAML and its variants, has emerged as a viable solution to accomplish this goal. One problem MAML encounters is its computational and memory burdens needed to compute the meta-gradients. We propose a new first-order variant of MAML that we prove converges to a stationary point of the MAML objective, unlike other first-order variants. We also show that the MAML objective does not satisfy the smoothness assumption assumed in previous works; we show instead that its smoothness constant grows with the norm of the meta-gradient, which theoretically suggests the use of normalized or clipped-gradient methods compared to the plain gradient method used in previous works. We validate our theory on a synthetic experiment.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes
In this work, we consider the problem of minimizing the sum of Moreau envelopes of given functions, which has previously appeared in the context of meta-learning and personalized federated learning. In contrast to the ex…
Federated LearningMeta-LearningPersonalized Federated LearningOn the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms
We study the convergence of a class of gradient-based Model-Agnostic Meta-Learning (MAML) methods and characterize their overall complexity as well as their best achievable accuracy in terms of gradient norm for nonconve…
Meta-LearningDirected-MAML: Meta Reinforcement Learning Algorithm with Task-directed Approximation
Model-Agnostic Meta-Learning (MAML) is a versatile meta-learning framework applicable to both supervised learning and reinforcement learning (RL). However, applying MAML to meta-reinforcement learning (meta-RL) presents …
Computational EfficiencyReinforcement LearningModel-Agnostic Meta-Policy Optimization via Zeroth-Order Estimation: A Linear Quadratic Regulator Perspective
Meta-learning has been proposed as a promising machine learning topic in recent years, with important applications to image classification, robotics, computer games, and control systems. In this paper, we study the probl…
image-classificationImage ClassificationMeta-LearningMulti-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity
Multi-agent reinforcement learning (MARL) has primarily focused on solving a single task in isolation, while in practice the environment is often evolving, leaving many related tasks to be solved. In this paper, we inves…