CS Events

PhD Defense

Geometric and Spectral Limitations in Generative Adversarial Networks


Download as iCal file

Monday, May 24, 2021, 10:00am - 12:00pm


Speaker: Mahyar Khayatkhoei

Location : Remote via Zoom


Dr. Ahmed Elgammal (advisor)

Dr. Abdeslam Boularias

Dr. Casimir Kulikowski

Dr. Dimitris Samars (outside member)

Event Type: PhD Defense

Abstract: Generative Adversarial Networks (GANs) have become one of the most successful and popular generative models in the recent years, with a wide variety of applications, such as image and audio manipulation and synthesis, style transfer, and semi-supervised learning, to name a few. The main advantage of GANs over their classical counterparts stems from the use of Deep Neural Networks (DNNs), in both the sampling process (generator) and the energy evaluation process (discriminator), which can utilize the ongoing revolution in the availability of data and computation power to effectively discover complex patterns. Yet, with this exceptional power, comes an exceptional limitation: the black-box behavior associated with DNNs, which not only places the profound promise of GANs under a shadow of mistrust, but also greatly slows down the efforts to improve the efficiency of these models. As such, studying GANs limitations and biases is critical for advancing their performance and usability in practice. The primary focus of this dissertation is to study two such limitations, namely a geometric limitation in generating disconnected manifolds, and a spectral limitation in learning distributions carried by high frequency components. We investigate these limitations both empirically and theoretically, unveil their causes and consequences, and propose and evaluate solutions for overcoming their adverse effects.


Join Zoom Meeting

Join by SIP
This email address is being protected from spambots. You need JavaScript enabled to view it.

Meeting ID: 933 9556 3726
Password: 068407
One tap mobile
+16465588656,,93395563726# US (New York)
+13017158592,,93395563726# US (Washington DC)

Join By Phone
+1 646 558 8656 US (New York)
+1 301 715 8592 US (Washington DC)
+1 312 626 6799 US (Chicago)
+1 669 900 9128 US (San Jose)
+1 253 215 8782 US (Tacoma)
+1 346 248 7799 US (Houston)
Meeting ID: 933 9556 3726
Find your local number: https://rutgers.zoom.us/u/aekwOeQSEH

Join by Skype for Business