Yehya Farhat, Ph.D.

I’m currently a research scholar at Syracuse University working with Prof. Venkata Gandikota to develop theoretical frameworks that can quantify the expressive capabilities of Graph and Convolutional Neural Networks.

My objective is to develop scalable and rigorous methods for explaining and enhancing AI models. Additionally, I am keenly interested in applying machine learning to overcome a broad spectrum of bottlenecks encountered in real-world engineering and scientific challenges.
I’m broadly interested in the following research themes:

• Leveraging AI models to tackle complex engineering and scientific problems: This entails leveraging data-driven algorithms that incorporate domain knowledge to learn fast approximate solutions for challenging PDEs and constrained optimization problems, while also developing frameworks to integrate constrained reasoning with deep learning, thereby enabling AI geared towards science and engineering.


• Understanding the expressive capabilities of deep learning models through a theoretical lens: My aim is to establish theoretical frameworks that can assist in establishing performance bounds for deep learning models and facilitate better model interpretability.


• Convex and Non-Convex Optimization: I focus on creating optimization methods that are both theoretically rigorous and empirically effective for large-scale problems. My particular interest lies in applying these techniques to enhance the training and general performance of deep learning models

Previously, I earned a M.Sc. in Computer Science from Syracuse University. In my last year of graduate studies, I completed my thesis on end-to-end constrained optimization learning under the supervision of Prof. Ferdinando Fioretto . Before that, I received a B.Sc in Computer Science and a minor in Mathematics from the American University of Beirut (AUB).

In my free time, I enjoy playing chess, staying active by playing football, and hitting the gym. I am also an avid writer passionate about sharing intriguing scientific topics I encounter. To stay updated, you can check out and subscribe to my newsletter below! Or find me on Medium.