arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1610.08210cs.GT
收藏

战略机器学习中透明度的代价

Price of Transparency in Strategic Machine Learning

Emrah Akyol, Cedric Langbort, Tamer Basar

摘要:

当用户(数据提供者)具有策略性时,算法的透明性会给算法设计者带来一定的代价,基于这一观察,本文研究了用户的策略意图对透明ML算法的设计和性能的影响。我们定量研究{ \bf价格的透明度}的背景下,战略分类算法,通过建模的问题作为一个非零和游戏之间的用户和算法设计者。具有透明算法的成本通过一个量来测量,在此称为透明度的价格,其是当算法是透明的(其允许用户具有策略性)时在Stackelberg均衡处的设计者成本与算法不透明的设置的设计者成本的比率。

英文摘要:

Based on the observation that the transparency of an algorithm comes with a cost for the algorithm designer when the users (data providers) are strategic, this paper studies the impact of strategic intent of the users on the design and performance of transparent ML algorithms. We quantitatively study the {\bf price of transparency} in the context of strategic classification algorithms, by modeling the problem as a nonzero-sum game between the users and the algorithm designer. The cost of having a transparent algorithm is measured by a quantity, named here as price of transparency which is the ratio of the designer cost at the Stackelberg equilibrium, when the algorithm is transparent (which allows users to be strategic) to that of the setting where the algorithm is not transparent.

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。

↑