In Defense of the Unitary Scalarization for Deep Multi-Task Learning

Understand

Recent multi-task learning research argues against unitary scalarization, where training simply minimizes the sum of the task losses.

• Several ad-hoc multi-task optimization algorithms have instead been proposed, inspired by various hypotheses about what makes multi-task settings difficult.
• The majority of these optimizers require per-task gradients, and introduce significant memory, runtime, and implementation overhead.
• We show that unitary scalarization, coupled with standard regularization and stabilization techniques from single-task learning, matches or improves upon the performance of complex multi-task optimizers in popular supervised and reinforcement learning settings.