Stat210B Mathematical Statistics
Stat210B Mathematical Statistics
Note: bCourses enrollment is not needed as of now. All materials will be available in shared Google Drive folders (links below) with your @berkeley.edu.
If you find any typos, mistakes or inaccuracies in scribes, please add them here (in some clear format).
Instructor: Nikita Zhivotovskiy
Office hours: Tuesday/Thursday 11:30 AM - 12:30 PM (315 Evans)
TA: Zhexiao Lin
TA office hours: TODO
Except for emergencies, use ED for questions. Home Assignments are in the Course Materials folder (requires @berkeley.edu account)
Final Exam: TODO
This is an advanced, fast-paced graduate course focused on non-asymptotic techniques in high-dimensional statistics. List of topics:
1. Concentration of measure inequalities.
2. Uniform law of large number. Metric entropy and chaining.
3. Non-asymptotic analysis of random matrices.
4. Localization and fast rates. Non-parametric least squares.
5. Lower-tail inequalities, sub-Gaussian estimators.
6. Selected questions on sparse recovery.
7. Information-theoretic upper bounds for density estimation and regression.
There will be four homework assignments during the course.
All necessary materials and resources are available in the shared Google Drive folders.
Assignments must be submitted by 11:59 PM on the due date. Late submissions will not be evaluated, except in cases of emergencies.
Homework must be submitted in digital text format only. Use LaTeX for written assignments.
Attendance is not mandatory but is strongly encouraged. This course does not offer video recordings.