Alexandros Dimakis

Dr. Dimakis received his Ph.D. in 2008 in Electrical Engineering and Computer Sciences from UC Berkeley and the Diploma degree from the National Technical University of Athens. He received an ARO young investigator award in 2014, the NSF Career award in 2011, a Google faculty research award, the Eli Jury dissertation award and several best paper awards. His research interests include information theory, coding theory and machine learning.


Research Interests: 
  • Information theory
  • Coding theory
  • Machine Learning
Current Research: 

Decision, Information, and Communications Engineering (DICE)

Research Labs & Affiliations: 

Wireless Networking and Communications Group (WNCG)

Select Publications

Matt Jordan, Justin Lewis, Alexandros G Dimakis. March 20, 2019. Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes.
Matt Jordan, Naren Manoj, Surbhi Goel, Alexandros G Dimakis. February 21, 2019. Quantifying Perceptual Distortion of Adversarial Examples.
Ethan R Elenberg, Rajiv Khanna, Alexandros G Dimakis, Sahand Negahban. December 2, 2018. Restricted strong convexity implies weak submodularity. Institute of Mathematical Statistics.
Qi Lei, Lingfei Wu, Pin-Yu Chen, Alexandros G Dimakis, Inderjit S Dhillon, Michael Witbrock. December 1, 2018. Discrete Attacks and Submodular Optimization with Applications to Text Classification.
Sungsoo Kim, Jin Soo Park, Christos G Bampis, Jaeseong Lee, Mia K Markey, Alexandros G Dimakis, Alan C Bovik. November 26, 2018. Adversarial Video Compression Guided by Soft Edge Detection.

Awards & Honors

2014 - Army Research Office (ARO) Young Investigator Award
2012 - Best Paper, Joint Information Theory and Communications Society
2012 - Google Faculty Research Award
2011 - NSF Career Award
2010 - Best Paper, ComSoc Data Storage Committee
2008 - Eli Jury Dissertation Award