Computational and Inferential Methods for High Dimensions and Massive Datasets (Fall 2012)
Course Information
September 4, 2012 - November 27, 2012
Principal Instructors: Various
Course Day and Time: Course was held at SAMSI (driving directions) in RTP on Tuesdays, 4:30-7:00 p.m. in Room 150.
Schedule: First class Tuesday, September 4, 2012 ; last class day, Tuesday, November 27, 2012
Course Description:
This course focused on fundamental methodological questions of statistics, mathematics and computer science posed by massive datasets, with applications to astronomy, high energy physics, and the environment.
Topics included:
- Data: where it comes from and how massive datasets can be efficiently managed, including dealing with missing and noisy data, anomalies and transient events
- Computing: how computational needs can be met by distributing computing over the available computational resources including cluster, cloud and GPU computing; efficient computational algorithms
- Visualization: data visualization to enhance human understanding
- Statistical Inference: problems and opportunities in high dimensional data; false discovery rates; regularization, Bayes and empirical Bayes; parametric, semi-parametric and non- parametric modeling; leveraging algorithms and computer resources
Registration for this course is processed through your respective university:
Duke: STA 790-03
NCSU: MA 810.001
UNC: STOR 940.1
Questions about the course or the MD program should be emailed to [email protected]