I am a machine learning scientist interested in constrained optimization and interpretable machine learning.

I currently work on bid optimization at StackAdapt. I got my PhD from the Computer Science department at the University of Toronto and Vector Institute. My Supervisors were Sheila McIlraith and Eldan Cohen. I did my undergraduate studies in Software Engineering at Sharif University of Technology.

My PhD was focused on utilizing combinatorial optimization, symbolic reasoning, and logical formalisms in machine learning. I have shown through my work that doing so enables interpretable machine learning, solution constraints, and ML models that are enhanced in rigorous reasoning capabilities. My work facilitates ML application to sensitive tasks where the model should be thoroughly understood and analyzed. It further supports tasks where domain-specific knowledge should be integrated in the solution. Lastly, it elevates common ML models such as LLMs by combining them with symbolic reasoning towards solving problems in domains such as planning, program synthesis, and vehicle routing.

At StackAdapt, I primarily lead the efforts on formulating and developing a new all-encompassing bid optimization algorithm. The new algorithm is aiming to support a wider array of goals and settings while addressing long-standing issues in transforming offline performance to online. It further provides flexibility and modularity that significantly improves efficient maintenance.