Timezone: »

The Advantage of Conditional Meta-Learning for Biased Regularization and Fine Tuning
Giulia Denevi · Massimiliano Pontil · Carlo Ciliberto

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1664

Biased regularization and fine tuning are two recent meta-learning approaches. They have been shown to be effective to tackle distributions of tasks, in which the tasks’ target vectors are all close to a common meta-parameter vector. However, these methods may perform poorly on heterogeneous environments of tasks, where the complexity of the tasks’ distribution cannot be captured by a single meta- parameter vector. We address this limitation by conditional meta-learning, inferring a conditioning function mapping task’s side information into a meta-parameter vector that is appropriate for that task at hand. We characterize properties of the environment under which the conditional approach brings a substantial advantage over standard meta-learning and we highlight examples of environments, such as those with multiple clusters, satisfying these properties. We then propose a convex meta-algorithm providing a comparable advantage also in practice. Numerical experiments confirm our theoretical findings.

Author Information

Giulia Denevi (University College of London)
Massimiliano Pontil (IIT & UCL)
Carlo Ciliberto (Imperial College London)

More from the Same Authors