Ph.D. Candidate in Electrical & Computer Engineering
Advised by Prof. Dionysis Kalogerias
I am a Ph.D. Candidate in Electrical and Computer Engineering at Yale University, advised by Prof. Dionysis Kalogerias. My work centers on constraint optimization. Especially the dynamics of, and optimization over, probability measures — drawing on stochastic optimization, statistical learning, duality theory, optimal transport, and information geometry.
Before Yale, I completed dual B.Sc. degrees in Computer Engineering and Pure Mathematics at Sharif University of Technology. Earlier, I ranked 9th nationwide in Iran’s National University Entrance Examination and earned a silver medal in the Iranian National Mathematical Olympiad.
My research is organized around four interconnected directions, connecting stochastic optimization, statistical learning, convex and nonconvex duality, information geometry, and decision-making under uncertainty.
Learning and decision-making when the data-generating distribution is uncertain or misspecified — ambiguity sets, risk measures, optimal transport, and dual reformulations that yield robust, statistically meaningful procedures.
Distributed learning with decentralized data — partial participation, client sampling bias, aggregation under distributional mismatch, and optimal-transport methods that align training dynamics with the intended global objective.
Constrained statistical learning beyond convexity — fairness, safety, coverage, and risk constraints — and when Lagrangian methods are justified via zero duality gap, dense hypothesis classes, and universal PAC learnability.
How sampling mechanisms shape learning and long-run statistical behavior — non-uniform participation, stochastic approximation, sampling-induced distribution shift, and gradient flows over probability measures.