|
Instructor: |
Alessandro Rinaldo (email: arinaldo at cmu dot edu) |
Course Description and Objectives: |
Minimax theory provides a general framework for quantifying the inherent hardness of statistical inferential tasks, such as estimation, hypothesis testing and confidence set building, and for assessing the optimality of a given methodology. Minimax analysis is ultimately concerned with deriving sharp lower bounds on the risk of a statistical task. Such lower bounds will depend on the sample size and, possibly, other properties of the underlying distribution. This mini will cover various techniques for computing minimax lower bounds and exemplify their usage in a variety of problems and applications borrowed from the current literature on high-dimensional statistics. The intended audience for this class is Ph.d. students in Statistics and Machine Learning. |
Syllabus |
Course work, class logistics and grading criteria are detailed in the syllabus. |
|
Lectures: |
Monday and Wednesday, 9:30am - 10:50am, WH5304. |
|
Office hour: |
By appointment. |
|
Schedule: |
Lecture schedule, scribe notes and homework assignments available here. |
|
References |
References and reading material available here. (The list will be regularly updated and expanded as the class progresses). |
|
Papers: |
A list of suggested papers for the in-class presentations is available here. |