arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.10863cs.LG
收藏

多校准的统一视角:多目标学习的博弈动力学

A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning

University of California, Berkeley(加州大学伯克利分校)

Nika Haghtalab, Michael I. Jordan, Eric Zhao

AI总结:

本文提出统一框架,将多校准问题建模为多目标学习,借助博弈动力学获得更强保证,并将k类多校准复杂度改进k的指数因子,同时拓展至群体公平性与多分布学习。

摘要:

我们为多校准预测器的设计与分析提供了一个统一框架。通过将多校准问题置于多目标学习的一般设定中——其中学习保证必须在一组分布和损失函数上同时成立——我们利用与博弈动力学的联系,为多种多样的多校准学习问题实现了最先进的保证。除了阐明现有多校准保证并极大简化其分析之外,我们的方法还产生了改进的保证,例如获得随群体规模平方根扩展的更强多校准条件,并将k类多校准的复杂度改进了k的指数因子。在多校准之外,我们利用这些博弈动力学来解决群体公平性和多分布学习研究中新出现的考量。

英文摘要:

We provide a unifying framework for the design and analysis of multicalibrated predictors. By placing the multicalibration problem in the general setting of multi-objective learning -- where learning guarantees must hold simultaneously over a set of distributions and loss functions -- we exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multicalibration learning problems. In addition to shedding light on existing multicalibration guarantees and greatly simplifying their analysis, our approach also yields improved guarantees, such as obtaining stronger multicalibration conditions that scale with the square-root of group size and improving the complexity of $k$-class multicalibration by an exponential factor of $k$. Beyond multicalibration, we use these game dynamics to address emerging considerations in the study of group fairness and multi-distribution learning.

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。

↑