Data Science

数据科学

• 批准号: 1000230475-2014
• 负责人: Plan, Yaniv
• 金额: $ 4.37万
• 依托单位: University of British Columbia
• 依托单位国家: 加拿大
• 项目类别: Canada Research Chairs
• 财政年份: 2019
• 资助国家: 加拿大
• 起止时间: 2019-01-01 至 2020-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=690916
• 关键词: Data; Science

A wonderful connection between theoretical mathematics and applied data analysis has developed in modern treatments of massive data, with deep theoretical understanding opening doors to new methods of data collection and analysis. For example, this has inspired surprising new methods of MR imaging with remarkable improvements in image quality. The key is to understand the structure of the signal lurking in the data -- in many cases this signal belongs to a complex, yet low-dimensional, set. I study these structures, how they behave under various forms of measurement acquisition, and how to take advantage of their low dimensionality to make powerful inferences in a computationally efficient manner.

在海量数据的现代处理中，理论数学与应用数据分析之间形成了一种奇妙的联系，深刻的理论理解为数据收集和分析的新方法打开了大门。例如，这激发了惊人的磁共振成像新方法，图像质量显著提高。关键是要理解隐藏在数据中的信号的结构——在许多情况下，这个信号属于一个复杂的低维集合。我研究这些结构，它们在各种形式的测量采集下的行为，以及如何利用它们的低维性以计算效率的方式进行强大的推断。