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 present a theoretical analysis suggesting that many specialized multi-task optimizers can be interpreted as forms of regularization. Moreover, we show that, when coupled with standard regularization and stabilization techniques from single-task learning, unitary scalarization matches or improves upon the performance of complex multi-task optimizers in both supervised and reinforcement learning settings. We believe our results call for a critical reevaluation of recent research in the area.

翻译：最近的多任务学习研究认为,不要单一的加速化,因为培训只是将任务损失的总和降到最低。相反,在各种假设的启发下,提出了几种特别的多任务优化算法,这些假设使多任务环境变得困难。这些优化者大多需要每个任务梯度,并引入重要的记忆、运行时间和执行间接费用。我们提出了一个理论分析,表明许多专门的多任务优化器可以被解释为正规化的形式。此外,我们表明,如果加上单一任务学习的标准正规化和稳定技术,单一任务学习、单一的超任务优化匹配或改进复杂多任务优化器在监管和强化学习环境中的性能,我们的结果要求对该地区最近的研究进行重要的重新评估。