论文标题
差异不平等的连续时间分析：概述和Desiderata
Continuous-time Analysis for Variational Inequalities: An Overview and Desiderata
论文作者
论文摘要
解决零和游戏的算法，多目标代理目标，或者更一般而言，差异不平等（VI）问题在一般问题上是不稳定的。由于越来越多的需求解决机器学习中的问题，近年来，这种不稳定性被强调为重大的研究挑战。在本文中，我们概述了在针对广泛的VI问题类别的分析和设计中使用连续时间观点的最新进展。我们的演示文稿在单目标问题和多目标问题之间取得了相似之处，突出了后者的挑战。我们还为适用于一般VIS的算法制定了各种desiderata，我们认为实现这些Desiderata可能会从对相关连续时间动态的理解中获利。
Algorithms that solve zero-sum games, multi-objective agent objectives, or, more generally, variational inequality (VI) problems are notoriously unstable on general problems. Owing to the increasing need for solving such problems in machine learning, this instability has been highlighted in recent years as a significant research challenge. In this paper, we provide an overview of recent progress in the use of continuous-time perspectives in the analysis and design of methods targeting the broad VI problem class. Our presentation draws parallels between single-objective problems and multi-objective problems, highlighting the challenges of the latter. We also formulate various desiderata for algorithms that apply to general VIs and we argue that achieving these desiderata may profit from an understanding of the associated continuous-time dynamics.
