arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.02576cs.GTcs.LG
收藏

回归均衡

Regression Equilibrium

Technion - Israeli Institute of Technology(以色列理工学院)

Omer Ben-Porat, Moshe Tennenholtz

摘要:

预测是一项经过充分研究的机器学习任务,预测算法是在线产品和服务的核心组成部分。尽管他们在提供基于预测的产品的在线公司之间的竞争中处于中心地位,但预测算法的\textit{strategic}使用仍然未被探索。本文的目的是研究预测算法的战略使用。我们引入了一种基于PAC学习框架的新的博弈论设置,其中每个玩家(也称为针对竞争的预测算法)寻求最大化它产生准确预测的点数之和,而其他人则没有。我们表明,旨在推广的算法可能会有意地错误预测一些点,以表现得比其他人更好的期望。我们分析了经验博弈,即,在给定的样本上导出博弈,证明了它总是具有一个纯纳什均衡,并证明了每一个反应较好的学习过程都是收敛的.此外,我们的学习理论分析表明,玩家可以,以高概率,学习一个近似的纯纳什均衡的整个人口使用少量的样本。

英文摘要:

Prediction is a well-studied machine learning task, and prediction algorithms are core ingredients in online products and services. Despite their centrality in the competition between online companies who offer prediction-based products, the \textit{strategic} use of prediction algorithms remains unexplored. The goal of this paper is to examine strategic use of prediction algorithms. We introduce a novel game-theoretic setting that is based on the PAC learning framework, where each player (aka a prediction algorithm aimed at competition) seeks to maximize the sum of points for which it produces an accurate prediction and the others do not. We show that algorithms aiming at generalization may wittingly mispredict some points to perform better than others on expectation. We analyze the empirical game, i.e., the game induced on a given sample, prove that it always possesses a pure Nash equilibrium, and show that every better-response learning process converges. Moreover, our learning-theoretic analysis suggests that players can, with high probability, learn an approximate pure Nash equilibrium for the whole population using a small number of samples.

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。

↑