No-regret Non-convex Online Meta-Learning

Abstract

The online meta-learning framework is designed for the continual lifelong learning setting. It bridges two fields: meta-learning which tries to extract prior knowledge from past tasks for fast learning of future tasks, and online-learning which deals with the sequential setting where problems are revealed one by one. In this paper, we generalize the original framework from convex to non-convex setting, and introduce the local regret as the alternative performance measure. We then apply this framework to stochastic settings, and show theoretically that it enjoys a logarithmic local regret, and is robust to any hyperparameter initialization. The empirical test on a real-world task demonstrates its superiority compared with traditional methods.

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Theoretical Models of Learning to Learn
• On First-Order Meta-Learning Algorithms
• AdaGrad stepsizes: Sharp convergence over nonconvex landscapes
• Online Meta-Learning

Cited by in corpus (1)

• Variable-Shot Adaptation for Online Meta-Learning