Mohammadreza MOUSAVI-KALAN is an Assistant Professor of Statistics at CREST-ENSAI. Previously, he was a postdoctoral fellow in the Department of Statistics at Columbia University. He received his Ph.D. in Electrical Engineering from the University of Southern California (USC) and his B.Sc. from Sharif University of Technology. Dr. MOUSAVI-KALAN's research focuses on theoretical foundations at the intersection of statistics and distributed computing. His primary interests include statistical machine learning, transfer learning, optimization theory, and distributed computing systems. He investigates how to design efficient algorithms that can leverage knowledge across related tasks while providing rigorous theoretical guarantees for learning procedures. His work addresses fundamental questions about sample complexity, computational efficiency, and statistical performance in modern machine learning settings. His publication record reveals a clear research trajectory from foundational work on distributed optimization (2018-2019) toward specialized topics in transfer learning and statistical hypothesis testing (2020-2025). A consistent theme across his work is establishing theoretical limits (minimax bounds, rate analyses) for practical machine learning problems. His recent publications focus on outlier detection, Neyman-Pearson classification frameworks, and transfer learning theory, demonstrating evolution toward more specialized statistical learning problems with practical applications. Dr. MOUSAVI-KALAN has established strong collaborative ties with researchers at USC, including Mahdi Soltanolkotabi, Salman Avestimehr, and Songze Li. His most influential work includes the Lagrange coded computing framework for distributed systems, which addresses critical challenges in resiliency, security, and privacy. His research bridges theoretical computer science, statistical learning theory, and practical distributed systems challenges, with implications for secure and efficient large-scale machine learning applications.
