Webinar Series: Deep Learning Methods and Theory

On Demystifying Adversarial Learning

Purdue Statistics is proud to announce the inaugural Distinguished Theme Seminar Series!

The idea is to introduce a timely and important research topic each year to the statistical audience via both introductory overview and in-depth research talks from leading researchers.  All are welcome! This year, our theme is "Deep Learning Methods and Theory” and the speakers are: 

August 28, 2020 - 3:30 - 4:30 pm ET

Lawrence Carin (Duke University)  

"On Demystifying Adversarial Learning"

Abstract:  There has been significant recent interest within the machine learning community on adversarial learning. In this setup an “actor,” or model, seeks to synthesize samples that are similar to those in the training set, while a “critic” seeks to distinguish the synthesized samples from the real data. The actor and critic play an adversarial “game,” and if this game is run effectively, highly realistic samples are manifested. In this talk we will derive such an adversarial learning setup from statistical first principles, and via this foundational perspective, we gain insight into failure mechanisms of such learning, and develop methods to mitigate them. We also show the application of adversarial learning to a diverse set of applications.

About the Speaker

Dr. Lawrence Carin earned the BS, MS, and PhD degrees in electrical engineering at the University of Maryland, College Park, in 1985, 1986, and 1989, respectively. In 1989 he joined the Electrical Engineering Department at Polytechnic University (Brooklyn) as an Assistant Professor, and became an Associate Professor there in 1994. In September 1995 he joined the Electrical and Computer Engineering (ECE) Department at Duke University, where he is now a Professor. He was ECE Department Chair from 2011-2014, the Vice Provost for Research from 2014-2019, and since 2019 he has served as Duke's Vice President for Research. From 2003-2014 he held the William H. Younger Distinguished Professorship, and since 2018 he has held the James L. Meriam Distinguished Professorship. Dr. Carin's research focuses on Machine Learning (ML), Artificial Intelligence (AI) and Applied Statistics. He publishes widely in the main ML/AI conferences, and he has also engaged in translation of research to practice. He was co-founder of the small business Signal Innovations Group, which was acquired by BAE Systems in 2014, and in 2017 he co-founded the company Infinia ML. He is an IEEE Fellow.

Future Speakers include:

September 4, 2020, 10:30 - 11:30 am ET

Heng Huang (Department of Electrical and Computer Engineering & Department of Biomedical Informatics, University of Pittsburgh)

"Distributed Machine Learning"

September 11, 2020, 10:30 - 11:30 am ET

Ying Nian Wu (Department of Statistics, University of California, Los Angeles) 

"A Representational Model of Grid Cells Based on Matrix Lie Algebras"

September 18, 2020, 10:30 - 11:30 am ET

Ruslan Salakhutdinov (Machine Learning Department, School of Computer Science, Carnegie Mellon University)

"Integrating Domain-Knowledge into Deep Learning"

We are able to take advantage of the online platform this year to broadcast these talks live via both Zoom meetings.

Detailed information about connecting and other schedule information are available at the webinar series website.