High-Dimensional Probability for Data Science

Taras Shevchenko National University of Kyiv, Fall 2022



Prof. Roman Vershynin, University of California, Irvine, USA

Email: rvershyn "at" uci "dot" edu

Curious about what I do? Check out this video.



Dr. Oksana Chernova, Taras Shevchenko National University of Kyiv

Email: oksanachernova "at" knu "dot" ua

When & Where

Lectures (Vershynin): MWF (Monday, Wednesday, Friday) 18:00-19:00 Kyiv time, by Zoom. The permanent Zoom link has been sent to your email. The link can also be found in the first announcement in Google classroom.

Discussion (Vershynin): 30 minutes after each lecture.

Discussion (Chernova): Tuesdays 14.30-15:15 Kyiv time, by Google Meet. The link has been sent to your email, and can also be found in the first announcement in Google classroom.

Description, Prerequisites & Textbook

Course description: This course will build probabilistic foundations for theoretical research in modern data science. The methods covered in this course form an essential toolbox for anyone looking to do mathematical work in machine learning, theoretical computer science, and signal processing.

Prerequisites: One semester of probability theory, and a course in linear algebra.

Textbook: R. Vershynin, High dimensional probability. An introduction with applications in Data Science. Cambridge University Press, 2018. Download the book here.


The grade will be determined by the homework. One homework set will be assigned every week. It is due each Sunday by 23:59, submitted to Google classroom. You can write the solutions in English or Ukrainian. Late homework will not be accepted.

Schedule & Homework

Lecture notes will be posted early morning before each class. Recorded lectures will posted shortly after each class. Homework will be posted one week before the due date.

Course webpage (this page): https://www.math.uci.edu/~rvershyn/teaching/2022-2023/probability-knu.html

Google classroom (homework submission and archive of annoucements): https://classroom.google.com/u/0/c/NTQ0Nzg3ODY4Mzk1