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

从相关数据中进行统计学习：学习理论、鲁棒算法和应用

• 批准号: 266702577
• 负责人: Professor Dr. Marius Kloft
• 金额: --
• 依托单位: Courant Institute of Mathematical Sciences
• 依托单位国家: 德国
• 项目类别: Independent Junior Research Groups
• 财政年份: 2015
• 资助国家: 德国
• 起止时间: 2014-12-31 至 2022-12-31
• 项目状态: 已结题
• 来源: https://gepris.dfg.de/gepris/projekt/266702577?language=en
• 关键词: Statistical; Learning; Dependent; Data; Theory

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).

机器学习是深入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，当数据表现出时间和空间相关性，或者在不同的实验条件或混杂因素下被记录时，这一假设可能会被违反。通过这项研究计划，我们建议努力建立一个理论上合理的、从相关数据中进行统计学习的一般框架。它的核心是开发新的算法，在这种情况下创造学习，并将其应用于科学和技术问题。该计划的一个特别重点是了解在独立环境下学习的理论基础(以便解释在哪些情况下算法可以很好地工作)。所有算法都嵌入了根据p值对训练模型进行自动和合理解释的框架中(以便领域专家进一步分析)。