arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2209.07463cs.LGcs.CYcs.DSmath.OC
收藏

约束优化的全预测子

Omnipredictors for Constrained Optimization

Stanford University(斯坦福大学)

Lunjia Hu, Inbal Livni-Navon, Omer Reingold, Chutong Yang

摘要:

全预测因子的概念(Gopalan,Kalai,Reingold,Sharan和Wieder ITCS 2021)提出了一种新的损失最小化范式。与基于已知损失函数学习预测器不同,与类$\mathcal C$中的假设损失相比,全预测器可以容易地进行后处理,以最小化丰富损失函数家族中的任何一个。它已被证明,这样的omnipredictors存在,并暗示(所有凸和Lipschitz损失函数)的概念,多校准的算法公平性文献。在本文中,我们介绍了全预测约束优化,并研究其复杂性和影响。我们引入的概念允许学习者不知道稍后将分配的损失函数以及稍后将施加的约束,只要用于定义这些约束的子群体是已知的。我们展示了如何获得omnipredictors约束优化问题,依赖于适当的变种多校准。我们还调查了这一概念的影响时,使用的约束是所谓的组公平的概念。

英文摘要:

The notion of omnipredictors (Gopalan, Kalai, Reingold, Sharan and Wieder ITCS 2021), suggested a new paradigm for loss minimization. Rather than learning a predictor based on a known loss function, omnipredictors can easily be post-processed to minimize any one of a rich family of loss functions compared with the loss of hypotheses in a class $\mathcal C$. It has been shown that such omnipredictors exist and are implied (for all convex and Lipschitz loss functions) by the notion of multicalibration from the algorithmic fairness literature. In this paper, we introduce omnipredictors for constrained optimization and study their complexity and implications. The notion that we introduce allows the learner to be unaware of the loss function that will be later assigned as well as the constraints that will be later imposed, as long as the subpopulations that are used to define these constraints are known. We show how to obtain omnipredictors for constrained optimization problems, relying on appropriate variants of multicalibration. We also investigate the implications of this notion when the constraints used are so-called group fairness notions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑