Cookies and Tracking help us to give you a better experience on our website
Splitting algorithms for training GANs
13.6.2023, 17:15 - 19:00
Speaker:Prof. Dr. Matthew Tam, University of Melbourne
Location:Institut für Numerische und Angewandte Mathematik, Lotzestraße 16-18MN 55Gras Geo Map
Organizer:Institut für Numerische und Angewandte Mathematik
Generative adversarial networks (GANs) are an approach to fitting generative models over complex structured spaces. Within this framework, the fitting problem is posed as a zero-sum game between two competing neural networks which are trained simultaneously. Mathematically, this problem takes the form of a saddle-point problem; a well-known example of the type of problem where the usual (stochastic) gradient descent-type approaches used for training neural networks fail. In this talk, we rectify this shortcoming by proposing a new method for training GANs that has: (i) a sounds theoretical foundation, and (ii) does not increase the algorithm's per iteration complexity (as compared to gradient descent). The theoretical analysis is performed within the framework of monotone operator splitting.
Search for keywords:
Host:Prof. Dr. Russell Luke
Export to your calendar (e.g., Outlook or iCal):