标题： 最小最大多任务学习和多任务学习的广义损失组合范式 显示英文标题

标题： Minimax Multi-Task Learning and a Generalized Loss-Compositional Paradigm for MTL

摘要： 自多任务学习（MTL）诞生以来，其操作方式一直是最小化经验风险的任务平均值。 我们引入了一种广义的损失组合范式用于MTL，该范式包含一系列公式作为子族。 这个谱系的一个端点是极小极大MTL：一种新的MTL公式，它最小化各个任务的经验风险的最大值。 通过某种对极小极大MTL的松弛，我们得到一个连续的MTL公式范围，涵盖极小极大MTL和经典MTL。 整个范式本身是损失组合的，作用于经验风险的向量。 它包含了极小极大MTL、它的松弛形式以及许多新的MTL公式作为特例。 我们从理论上证明了极小极大MTL在学习到学习（LTL）测试设置中，倾向于避免新抽取测试任务的最坏结果。 在MTL和LTL测试设置中，几种MTL公式在合成和实际问题上的结果令人鼓舞。 显示英文摘要

摘要： Since its inception, the modus operandi of multi-task learning (MTL) has been to minimize the task-wise mean of the empirical risks. We introduce a generalized loss-compositional paradigm for MTL that includes a spectrum of formulations as a subfamily. One endpoint of this spectrum is minimax MTL: a new MTL formulation that minimizes the maximum of the tasks' empirical risks. Via a certain relaxation of minimax MTL, we obtain a continuum of MTL formulations spanning minimax MTL and classical MTL. The full paradigm itself is loss-compositional, operating on the vector of empirical risks. It incorporates minimax MTL, its relaxations, and many new MTL formulations as special cases. We show theoretically that minimax MTL tends to avoid worst case outcomes on newly drawn test tasks in the learning to learn (LTL) test setting. The results of several MTL formulations on synthetic and real problems in the MTL and LTL test settings are encouraging.