I am a Third year Ph.D. student in Computer Science at University of Maryland. I am also a part-time researcher at Comcast Applied Artificial Intelligence Research Lab. I work on Machine Learning and Optimization. I am interested in fast, low-complexity solutions to real-world problems.
My research has always been covering a very broad range of Machine Learning topics. However, my recent research efforts have been mostly focused on two major areas: 1) Recommendation Systems, Content Discovery, and Information Retrieval and 2) Machine Learning Algorithm and Applications in Software Engineering.
I also develop and maintain the Project Mangrove website. Feel free to check it out and help us furthur our research goals.

I did my undergraduate studies in Software Engineering at Sharif University of Technology. I also co-founded and managed an educational center for helping high school students prepare for Olympiads while I was doing my undergrad.

I'm open to all sorts of collaboration. Please feel free to get in touch. You can find my email here.


Recent News and updates (View all)

Aug. 18, 2017 - Researcher Position

I'm pleased to announce that I will continue my work with Comcast Applied Artificial Intelligence Research Lab, as a part-time researcher. I will be working on Recommendation Systems, Content Discovery, and Information Retrieval.

April 23, 2017 - Paper Acceptance

Our paper titled "Learning a Classifier for False Positive Error Reports Emitted by Static Code Analysis Tools" has been accepted into MAPL 2017.

View All

Select Honors & Awards

Recipient of University of Maryland Dean’s Fellowship

Gold Medal in Iranian National Olympiad in Informatics

Outstanding Student - Sharif University of Technology

Selected as Iranian National Scientific Elite

Recent Publications (View all)

Learning a Classifier for False Positive Error Reports emitted by Static Code Analysis Tools

Ugur Koc, Parsa Saadatpanah, Jeffrey S. Foster, and Adam A. Porter

MAPL 2017 - PLDI 2017

View All

Recent Projects (View all)

Inverse Reinforcement Learning with Suboptimal Experts

Existing works in Reinforcement Learning field either explicitly assume the expert trajectories are all optimal, or their algorithms tend to work poorly for sub-optimal expert trajectories. We propose a new algorithm which is much more resilient to sub-optimal trajectories.

Variance Reduction for Kacsmarz methods

Kacsmarz methods are very popular optimization methods but they are prone to non existence of optimal solution and noise in the data. My research focused on utilizing Variance Reduction algorithms to make Kacsmarz methods more robust.


Flipping is a local and efficient operation to construct the convex hull in an incremental fashion. However, it is known that the traditional flip algorithm is not able to compute the convex hull when applied to a polyhedron in R3. Our novel Flip-Flop algorithm is a variant of the flip algorithm. It overcomes the deficiency of the traditional one to always compute the convex hull of a given star-shaped polyhedron with provable correctness.

View All


Send me an email at [My First Name]@cs.umd[dot]edu