Course Description
Rapid growth in computer power has made it possible to study complex physical phenomena that might otherwise be too time-consuming or expensive to observe. This course will introduce state-of-the-art concepts and algorithms concerning the design and analysis of computer experiments.
Additional Requirements for Graduate Students:
Additional and/or alternative problems of a more challenging nature will be required for graduate students on homework and exams.
Athena Title
Computer Experiments
Undergraduate Prerequisite
(STAT 4220 and STAT 4510/6510) or permission of department
Graduate Prerequisite
STAT 6430 or permission of department
Semester Course Offered
Offered fall and spring
Grading System
A - F (Traditional)
Course Objectives
The course is meant to provide the mathematical foundations and computational skills for the design and analysis of computer experiments, on topics at the interface between machine learning, spatial statistics, meta-modeling (i.e., emulations), design of experiments, optimization, and active learning. Students will demonstrate competence through individual or group programming projects, labs, and examinations throughout the course. Additional topics will be covered at the discretion of the instructor. After taking this course, the students should be able to design and analyze data from simulators, synthesize under uncertainty, visualize, design new experiments, and make informed decisions.
Topical Outline
Gaussian process (GP) regression for flexible nonparametric and nonlinear modeling, applications to uncertainty quantifications, sensitivity analysis, calibration of computer models, and optimization under uncertainty. Space-filling designs, sequential designs, and active learning. Advanced topics will include treed partitioning, local GP approximation, modeling of simulation experiments, and response surface methodology. Implementation in R will be required. Computing and writing clean codes will be emphasized. Other modern areas of computer experiments may be covered at the discretion of the instructor.