Please note: This PhD seminar will be given online.
Guojun
Zhang, PhD
candidate
David
R.
Cheriton
School
of
Computer
Science
Supervisors: Professors Pascal Poupart and Yaoliang Yu
Min-max formulations have attracted great attention in the ML community due to the rise of deep generative models and adversarial methods, while understanding the dynamics of gradient algorithms for solving such formulations has remained a grand challenge. As a first step, we restrict to bilinear zero-sum games and give a systematic analysis of popular gradient updates, for both simultaneous and alternating versions. We provide exact conditions for their convergence and find the optimal parameter setup and convergence rates. In particular, our results offer formal evidence that alternating updates converge “better” than simultaneous ones.
To join this PhD seminar on Zoom, please go to https://vectorinstitute.zoom.us/j/93656462222?pwd=UXFKRUIvcXZnWjUxNkpBeGcrZnFvQT09.