Soheil Feizi

Assistant Professor, CS @ UMD

I am a faculty in Computer Science department at University of Maryland, College Park (UMD). I am also a member of University of Maryland Institute for Advanced Computer Studies (UMIACS) and affiliated with the Electrical and Computer Engineering (ECE) Department at UMD. My research spans various theoritical and practical aspects of Machine Learning.
Before joining UMD, I was a a post-doctoral researcher at Stanford University . I received my Ph.D. and M.Sc. in Electrical Engineering and Computer Science, with a minor degree in Mathematics, at MIT.

Research

My research focuses on understanding various theoretical and practical aspects of machine learning and statistical inference problems. In my group, we are working on problems related to Generative Adversarial Networks (GANs), Variational AutoEncoders (VAEs), Adversarial examples, the optimization landscape of deep learning, its interpretability and generalization, etc.

Read More

Teaching

I am teaching CMSC 726 (the graduate level Machine Learning Course) in Fall 2018. In this course, we will start with classical learning models and work towards modern problems such as GANs, VAEs and adversarial examples. This course will be a mix of theory and applications. 

Read More

Note to Prospective Students:

I am looking for students and post-docs with a strong mathematical background who are interested in working in theoritical and practical aspects of machine learning.

Information for prospective students can be found here.

Read More

NEWS:

New Paper on arXiv

3
OCT, 2018

Our work titled Entropic GANs meet VAEs [paper] is available on arXiv.

Paper Accepted!

29
SEPT, 2018

Our work on Spectral Alignment of Graphs [paper] has been accepted to IEEE Transactions on Network Science and Engineering.

Talk at Quantum Machine Learning Workshop

27
SEPT, 2018

I gave an invited talk titled Generative Adversarial Networks: Formulation, Design and Computation in the QML workshop.

Paper Accepted!

5
SEPT, 2018

Our work on understanding the Landscape of Neural Networks [paper] has been accepted to NIPS.

New Paper on arXiv

5
SEPT, 2018

Our work on Adversarial Examples [paper] is available on arXiv.

Paper Accepted!

20
JUL, 2018

Our work on Source Inference in Graphs [paper] has been accepted to IEEE Transactions on Network Science and Engineering.

Machine Learning Course

01
JUL, 2018

I am teaching CMSC 726 in Fall 2018. See the course webpage here.

First Day @ UMD

01
JUL, 2018

I am officially starting my faculty career at CS@UMD. I am also a member of UMIACS.

Talk @ Google Research

28
JUN, 2018

I am giving a talk titled "GANs: model-based or model-free?" in google research.