On the Statistical Benefits of Curriculum Learning

Abstract

Curriculum learning (CL) is a commonly used machine learning training strategy. However, we still lack a clear theoretical understanding of CL's benefits. In this paper, we study the benefits of CL in the multitask linear regression problem under both structured and unstructured settings. For both settings, we derive the minimax rates for CL with the oracle that provides the optimal curriculum and without the oracle, where the agent has to adaptively learn a good curriculum. Our results reveal that adaptive learning can be fundamentally harder than the oracle learning in the unstructured setting, but it merely introduces a small extra term in the structured setting. To connect theory with practice, we provide justification for a popular empirical method that selects tasks with highest local prediction gain by comparing its guarantees with the minimax rates mentioned above.

References in corpus (7)

• Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
• The Benefit of Multitask Representation Learning
• On the Theory of Transfer Learning: The Importance of Task Diversity
• Few-Shot Learning via Learning the Representation, Provably
• Few-shot Domain Adaptation by Causal Mechanism Transfer
• Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks
• Representation Learning Beyond Linear Prediction Functions