In machine learning, the goal of multi-task learning (MTL) is to optimize multiple objectives together. Recent works, for example, Multiple Gradient Descent Algorithm (MGDA) and its variants, show promising results with dynamically adjusted weights for different tasks to mitigate conflicts that may potentially degrade the performance on certain tasks. Despite the empirical success of MGDA-type methods, one major limitation of such methods is their computational inefficiency, as they require access to all task gradients. In this paper we introduce MARIGOLD, a unified algorithmic framework for efficiently solving MTL problems. Our method reveals that multi-task gradient balancing methods have a hierarchical structure, in which the model training and the gradient balancing are coupled during the whole optimization process and can be viewed as a bi-level optimization problem. Moreover, we showcase that the bi-level problem can be solved efficiently by leveraging zeroth-order method. Extensive experiments on both public datasets and industrial-scale datasets demonstrate the efficiency and superiority of our method.

翻译：在机器学习中，多任务学习（MTL）的目标是同时优化多个目标。近期工作，例如多梯度下降算法（MGDA）及其变体，通过动态调整不同任务的权重来缓解可能损害某些任务性能的冲突，已展现出有希望的结果。尽管MGDA类方法在实证上取得了成功，但此类方法的一个主要局限是其计算效率低下，因为它们需要获取所有任务的梯度。本文中，我们引入了MARIGOLD，一个用于高效解决MTL问题的统一算法框架。我们的方法揭示了多任务梯度平衡方法具有层次结构，其中模型训练和梯度平衡在整个优化过程中相互耦合，可视为一个双层优化问题。此外，我们展示了该双层问题可通过利用零阶方法高效求解。在公共数据集和工业级数据集上进行的大量实验证明了我们方法的效率与优越性。