Department of Prevention Medicine Biostatistics Seminar Series: Error analysis of generative adversarial network

The Division of Biostatistics at the Department of Preventive Medicine invites you to attend the following seminar.

Time: Thursday, March 28, 2:00 PM-3:00 PM CT

Location:4th Floor Conference Room 400 in the Doctors Office Building at 66 N. Pauline Street, Memphis, TN 38105.

Please park in the multi-story parking garage adjacent to the Doctors Office Building, and bring your parking ticket with you so we can validate it.

ZOOM Virtual Room Connection:Register in advance for this meeting

Seminar Website:https://www.eventcreate.com/e/biostatisticsseminar

Speaker Bio: https://math.olemiss.edu/hailin-sang/

Error analysis of generative adversarial network

Hailin Sang, Ph.D.

Department of Mathematics, University of Mississippi

The generative adversarial network (GAN) is an important model developed for high-dimensional distribution learning in recent years. However, there is a pressing need for a comprehensive method to understand its error convergence rate. In this research, we focus on studying the error convergence rate of the GAN model that is based on a class of functions encompassing the discriminator and generator neural networks. These functions are VC type with bounded envelope function under our assumptions, enabling the application of the Talagrand inequality. By employing the Talagrand inequality and Borel-Cantelli lemma, we establish a tight convergence rate for the error of GAN. This method can also be applied on existing error estimations of GAN and yields improved convergence rates. In particular, the error defined with the neural network distance is a special case error in our definition. This talk is based on the project jointly with Mahmud Hasan.

Public link

Please use the above public link if you want to share this noodl on another website.