Skip to yearly menu bar Skip to main content


Provable Guarantees for Gradient-Based Meta-Learning

Nina Balcan · Mikhail Khodak · Ameet Talwalkar

Pacific Ballroom #253

Keywords: [ Transfer and Multitask Learning ]


We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods. Our method is the first to simultaneously satisfy good sample efficiency guarantees in the convex setting, with generalization bounds that improve with task-similarity, while also being computationally scalable to modern deep learning architectures and the many-task setting. Despite its simplicity, the algorithm matches, up to a constant factor, a lower bound on the performance of any such parameter-transfer method under natural task similarity assumptions. We use experiments in both convex and deep learning settings to verify and demonstrate the applicability of our theory.

Live content is unavailable. Log in and register to view live content