Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD

Abstract

We propose a new computationally-efficient first-order algorithm for Model-Agnostic Meta-Learning (MAML). The key enabling technique is to interpret MAML as a bilevel optimization (BLO) problem and leverage the sign-based SGD(signSGD) as a lower-level optimizer of BLO. We show that MAML, through the lens of signSGD-oriented BLO, naturally yields an alternating optimization scheme that just requires first-order gradients of a learned meta-model. We term the resulting MAML algorithm Sign-MAML. Compared to the conventional first-order MAML (FO-MAML) algorithm, Sign-MAML is theoretically-grounded as it does not impose any assumption on the absence of second-order derivatives during meta training. In practice, we show that Sign-MAML outperforms FO-MAML in various few-shot image classification tasks, and compared to MAML, it achieves a much more graceful tradeoff between classification accuracy and computation efficiency.

References in corpus (6)

• Neural Architecture Search with Reinforcement Learning
• On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization
• A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic
• Bilevel Optimization: Convergence Analysis and Enhanced Design
• Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
• When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications