Dear all,
Join us for our upcoming talk in the
STAR seminar series
on
Wednesday, February 25th, from 11:00 to 12:00 (Oslo time).
As always, the talk will take place in a hybrid format: participants in Oslo can attend the talk in
Room 723 in Niels Henrik Abels hus, whereas the international audience will be able to follow the talk via
Zoom.
The speaker is Yi Feng (Aarhus University)
with the talk:
Title: Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games
Abstract: Since Polyak's pioneering work, heavy ball momentum has been widely studied in minimization problems. However, its role in min-max games remains largely unexplored. As a key component of practical min-max algorithms like Adam, this gap limits
their effectiveness. In this talk, I will present a continuous-time analysis for heavy ball momentum in min-max games. I will focus on two aspects: convergence to equilibrium and implicit gradient regularization, which describe how momentum shapes the interaction
between algorithmic trajectories and the geometry of the min-max loss landscape. We will see that the behavior of heavy ball momentum in min-max games is significantly different from that in minimization.
Bio: Yi Feng is a Postdoctoral researcher at Aarhus University. His research focuses on understanding the learning dynamics in games and their applications in machine learning. His research is supported by a Danish Data Science Academy Postdoctoral Fellowship.
We are looking forward to seeing you!
Best regards,
Giulia, Leonardo, Pere, and David