The Advantage of Conditional Meta-Learning for Biased Regularization and Fine-Tuning
This work addresses the problem of poor performance in heterogeneous task environments for meta-learning practitioners, offering a conditional approach that is incremental over existing methods.
The paper tackles the limitation of biased regularization and fine-tuning in heterogeneous task distributions by introducing conditional meta-learning, which maps task side information to appropriate meta-parameters, and demonstrates its advantage through theoretical characterization and numerical experiments.
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.