In the second installment of OT+X series we take X=ML (Machine Learning).
The first part of the course will cover the mathematical basics of OT and introduce the geometry of Wasserstein spaces.
The second part of the course will cover computational aspects of OT and describe the central role played by OT in convergence analysis of stochastic algorithms for deep learning, in distributionally robust statistical learning,
and in combinatorial or geometrical problems arising in data science applications.
The course is meant for a wide audience including graduate students and industry professionals. Prior knowledge of real analysis, probability, statistics, and machine learning will be particularly helpful. The course will be interspersed with numerical illustrations. Familiarity with coding in Python or R is a plus.
This will be an online course taught by Zoom. Zoom links will be provided to students once they are added to the course canvas. Please see below.
Registration information for students at the University of Washington: the course is listed as Math 581 D and Stat 591 A. You can register for either of these courses and get credit. You will get access to notes and video recording via Canvas.
Registration information for Canadian students: This course is available via University of British Columbia as Math 566 and can be registered under the Western Dean's Agreement. Please contact Prof. Young-Heon Kim for registration information. Please contact me at the beginning of the class to add you to the Canvas webpage for notes and videos.
Information for students who are outside the PIMS network of universities: At this point we cannot register students outside the network for credit. But you are welcome to audit the course. Please send me your contact email (must be gmail) right before the course starts so that I can add you to Canvas webpage where you can access the notes and recordings of the lectures.
Some details about the class:
Feel free to contact me for any questions.