Machine Learning Lecture: Nisheeth Vishnoi

Description

Nisheeth Vishnoi, a professor of computer science at Yale University, will give a talk entitled "Equilibrium in Nonconvex-Nonconcave Min-Max Optimization and GANs."

Please attend the event by using the Zoom link (passcode: jhuml).

Abstract:

While there has been incredible progress in convex and nonconvex minimization, many problems in machine learning are in need of efficient algorithms to solve min-max optimization problems. However, unlike minimization, where algorithms can always be shown to converge to some local minimum, there is no notion of local equilibrium in min-max optimization that exists for general nonconvex-nonconcave functions. We will present new notions of local equilibria that are guaranteed to exist, efficient algorithms to compute them, and implications to GANs.

Read two blog posts with links to the respective papers here and here.