I recently joined Lightmatter as an Applied Scientist. This webpage will be moved to a new domain. Stay tuned.


I am a Postdoctoral Fellow at Yale University and the VA Connecticut Healthcare System, working for Amy Justice. I have been working on mathematics of deep learning functions and their interpretation in different contexts. I am also interested in Fairness, Accountability, and Transparency in applications of AI. Recently, I am working on biomedical data and medical images.

I completed my PhD in the Department of Computer Science at University of Maryland, College Park. My research advisor and mentor at UMD was Professor Dianne P. O’Leary. My main research interests are scientific computing, machine learning, and solving hard optimization problems.

For my dissertation, I worked on interpretation of neural networks and applications of homotopy methods. We developed mathematical methods to study trained neural networks as nonlinear functions, interpret their behavior, study their decision boundaries, and to improve and debug them. Our research has implications for adversarial robustness of deep learning models and their generalization, too.

More recently I have been working on a project about extrapolation in deep learning and machine learning. I have proposed that 4 phenomenon should be studied together: 1- Generalization in deep learning, 2- Extrapolation as the functional task of image classification models, 3- Decision boundaries that partition the domain of these functions, and 4- Over-parameterization as a necessary condition for having control over the extension of decision boundaries outside the convex hull of training set. Read more about this project here.

In summer 2018, I was at the Los Alamos National Laboratory for their Applied Machine Learning Fellowship. We finished a project about interpretation of Gaussian graphical models for unsupervised learning. It is published in the proceedings of a SIAM conference.

I like to solve challenging optimization problems in different contexts. I am comfortable with nonlinear optimization problems, integer programming, and linear programming. During my graduate coursework, I took Scientific Computing I and II, Nonlinear Optimization II, Integer Programming, Sparsity and Machine Learning, Machine Learning, High Performance Computing, Computational Geometry, and several other courses.

I have worked on real-time optimization problems in Humanitarian Aid delivery systems and Freight transportation systems. We developed a probabilistic framework to optimize the decisions. Our formulation is nonlinear and non-convex, and we designed a homotopy algorithm to solve it in real-time.

In Fall 2018, I received the Graduate School’s Outstanding Teaching Assistant Award. That semester, I was a TA for the course CMSC460 “Computational Methods”. In 2020, I received the Medical Informatics Advanced Fellowship at Yale and VA CT Healthcare System.

I am also a licensed structural engineer. Before studying computer science, I was a structural design engineer. I still love designing bridges and interchanges.

When I am free, I like reading books about science and humanities, and I like running/hiking.