The introduction of the European Union's (EU) set of comprehensive regulations relating to technology, the General Data Protection Regulation, grants EU citizens the right to explanations for automated decisions that have significant effects on their life. This poses a substantial challenge, as many of today's state-of-the-art algorithms are generally unexplainable black boxes. Simultaneously, we have seen an emergence of the fields of quantum computation and quantum AI. Due to the fickle nature of quantum information, the problem of explainability is amplified, as measuring a quantum system destroys the information. As a result, there is a need for post-hoc explanations for quantum AI algorithms. In the classical context, the cooperative game theory concept of the Shapley value has been adapted for post-hoc explanations. However, this approach does not translate to use in quantum computing trivially and can be exponentially difficult to implement if not handled with care. We propose a novel algorithm which reduces the problem of accurately estimating the Shapley values of a quantum algorithm into a far simpler problem of estimating the true average of a binomial distribution in polynomial time.
翻译:引入欧洲联盟(欧盟)有关技术的一套全面条例,即《数据保护总条例》,赋予欧盟公民解释对其生活有重大影响的自动决定的权利。这构成了巨大的挑战,因为当今许多最先进的算法一般都是无法解释的黑盒。与此同时,我们看到量子计算和量子AI领域的出现。由于量子信息的易变性质,可解释性的问题被放大,因为量子系统测量摧毁了信息。因此,需要对量子AI算法进行热后解释。在传统背景下,Shapley值的合作游戏理论概念已经适应于热后解释。然而,这种方法并没有被轻描淡写地用于量子计算,如果不小心处理,则可能极难执行。我们提出了一个新的算法,将准确估计量子算法的损耗值的问题降低到一个更简单的问题,即估算多瑙时代的二元分布的真实平均数。