Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness

Understand

Representation multi-task learning (MTL) has achieved tremendous success in practice.

• However, the theoretical understanding of these methods is still lacking.
• Most existing theoretical works focus on cases where all tasks share the same representation, and claim that MTL almost always improves performance.
• Nevertheless, as the number of tasks grows, assuming all tasks share the same representation is unrealistic.