turkmath.org

In the first part of the presentation, we will talk about some numerical methods for solving the stochastic non-smooth convex optimization problems with functional constraints, and for solving the same problem in the online setting. We will show new modifications of adaptive mirror descent algorithms with estimates of the convergence rate of the proposed methods.  In the second part of the presentation, we will talk about gradient-type adaptive methods for relatively Lipschitz and relatively smooth convex optimization problems.

Link to the seminar is:

https://teams.microsoft.com/l/meetup-join/19%3a0ae91f7b86a24e8fa1d818a6f74b22a1%40thread.tacv2/1646598677346?context=%7b%22Tid%22%3a%22066690f2-a8a6-4889-852e-124371dcbd6f%22%2c%22Oid%22%3a%22a343f6fd-86f8-4abe-95cf-3c7f4ad5f0ca%22%7d