Statistical Learning from Dependent Data:Learning Theory, Robust Algorithms, and Applications

机器学习是彻底分析经验数据的关键技术之一。机器学习中最常见的假设之一是经验数据是由独立的随机变量实现的。然而，在实践中，当数据显示出时间和空间依赖性或在不同的实验条件或混杂因素下记录时，这一假设可能会被违反。有了这个研究计划，我们建议朝着从依赖数据中进行统计学习的理论健全和一般框架工作。其核心在于新算法的发展，在这种特殊情况下创造学习，并将其应用于科学和技术问题。该计划的一个特别重点是获得对依赖环境中学习的理论基础的理解（为了解释算法在哪些情况下可以正常工作）。所有算法都嵌入到一个框架中，根据p值对训练模型进行自动和合理的解释（以便于领域专家进一步分析）。

Machine learning constitutes one of the key technologies to thoroughly analyze empirical data. One of the most common assumptions in machine learning is that the empirical data is realized from independent random variables. However, in practice this assumption can be violated when the data exhibits temporal and spatial dependencies or is recorded under varying experimental conditions or confounding factors. With this research program we propose to work toward a theoretically sound and general framework of statistical learning from dependent data. At the heart of which lies the development of novel algorithms creating learning in particular cases of this settings and their application to problems from the sciences and technology. A particular emphasis of the program is on gaining an understanding of the theoretical foundations of learning in dependent settings (in order to explain under which circumstances the algorithms will work fine). All algorithms are embedded into a framework of automatic and sound interpretation of the trained models in terms of p-values (in order to facilitate further analysis by domain experts).