Denevi, G; Pontil, M; Ciliberto, C; (2020) The Advantage of Conditional Meta-Learning for Biased Regularization and Fine-Tuning. In: Proceedings of NeurIPS 2020: Thirty-fourth Conference on Neural Information Processing Systems. Neural Information Processing Systems: Virtual conference.

Preview

Text NeurIPS-2020-the-advantage-of-conditional-meta-learning-for-biased-regularization-and-fine-tuning-Paper.pdf - Published Version Download (1MB) | Preview

Abstract

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.

Download activity - last month

Export as CSVJSONXML

Download activity - last 12 months

Export as CSVJSONXML

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item