Research/Areas of Interest
High-Dimensional data analysis: Matrix completion, compressive sensing, and structured sparse recovery.
Mathematical foundations of AI: Interpretable machine learning, dictionary learning, and geometry-aware representations.
Applied optimization: Distance geometry, large-scale kernel methods, and algorithm unrolling for signal processing
Education
- PhD, Mathematics, Rensselaer Polytechnic Institute, United States, 2019
- MS, Aeronautics and Astronautics, Massachusetts Institute of Technology, United States, 2014
- BS, Mathematics, Massachusetts Institute of Technology, United States, 2012
Biography
My research focuses on developing scalable and robust algorithms for problems at the intersection of applied mathematics, machine learning, and data science. By leveraging low-dimensional structures, such as sparsity and low-rankness, I design algorithms capable of handling noisy and incomplete observations while extracting interpretable representations from complex datasets. Using tools from optimization, high-dimensional probability, and numerical linear algebra, my work combines theoretical analysis with principled algorithm design for problems in areas such as distance geometry, structured sparse recovery, large-scale kernel methods, and interpretable machine learning via localized dictionaries. These mathematical foundations motivate practical solutions in applications including sensor localization, target tracking, geometry reconstruction, and the integration of physical or experimental constraints into machine learning models.