Conducted PhD research at Stanford University, focusing on the design and implementation of machine learning and optimization algorithms.
Education
PhD: Stanford University, advised by Madeleine Udell; MS: Center for Applied Mathematics at Cornell University, major in Applied Mathematics; BS: Rensselaer Polytechnic Institute, major in Mathematics.
Background
Research Interests: machine learning, optimization, and numerical linear algebra. PhD work focused on designing efficient optimization algorithms with strong theoretical guarantees for large-scale machine learning and data analysis. Topics include linear system solving, composite optimization, and empirical risk minimization. A recurring theme in his work is leveraging randomized numerical linear algebra to dramatically accelerate computation, while maintaining rigorous convergence guarantees. Applications of his work include generalized linear models, kernel learning, and physics-informed neural networks.
Miscellany
Currently seeking full-time opportunities in industry.