In the last few years, the application of machine learning methods has become increasingly relevant in different fields of physics. One of the most significant subjects in the theory of open quantum systems is the study of the characterization of non-Markovian memory effects that emerge dynamically throughout the time evolution of open systems as they interact with their surrounding environment. Here we consider two well-established quantifiers of the degree of memory effects, namely, the trace distance and the entanglement-based measures of non-Markovianity. We demonstrate that using machine learning techniques, in particular, support vector machine algorithms, it is possible to estimate the degree of non-Markovianity in two paradigmatic open system models with high precision. Our approach can be experimentally feasible to estimate the degree of non-Markovianity, since it requires a single or at most two rounds of state tomography.

中文翻译：

---

使用机器学习估计非马尔可夫程度

在过去的几年中，机器学习方法的应用在物理的不同领域变得越来越重要。开放式量子系统理论中最重要的主题之一是对非马尔可夫记忆效应的表征的研究，该效应在开放式系统与周围环境相互作用的整个过程中动态地出现。在这里，我们考虑记忆效应程度的两个公认的量词，即走线距离和基于非纠缠度的纠缠度量。我们证明了使用机器学习技术，尤其是支持向量机算法，可以在两个范例开放系统模型中以高精度估计非马尔可夫性的程度。