Poster

Conditional Meta-Learning of Linear Representations

Giulia Denevi · Massimiliano Pontil · Carlo Ciliberto

Keywords: [ Statistical Learning Theory ] [ Conditional Meta-Learning ] [ Online Learning ] [ linear representation learning ]

[ Abstract ]
[ Poster [ OpenReview
 
Spotlight presentation: Lightning Talks 3B-1
Wed 7 Dec 9 a.m. PST — 9:15 a.m. PST

Abstract:

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks’ distribution cannot be captured by a single representation. In this work we overcome this issue by inferring a conditioning function, mapping the tasks’ side information (such as the tasks’ training dataset itself) into a representation tailored to the task at hand. We study environments in which our conditional strategy outperforms standard meta-learning, such as those in which tasks can be organized in separate clusters according to the representation they share. We then propose a meta-algorithm capable of leveraging this advantage in practice. In the unconditional setting, our method yields a new estimator enjoying faster learning rates and requiring less hyper-parameters to tune than current state-of-the-art methods. Our results are supported by preliminary experiments.

Chat is not available.