I am an Assistant Professor in Computer Science at the University of North Carolina at Charlotte and Co-Director of the Charlotte Machine Learning Lab. Prior to joining UNC Charlotte, I was a Postdoctoral Fellow at the Department of Applied Mathematics and Statistics at Johns Hopkins University (mentored by Mauro Maggioni) after completing a Ph.D. in Mathematics at Technical University of Munich in 2019, advised by Felix Krahmer. I obtained M.Sc. and B.Sc. degrees in Mathematics from TU Munich in 2015 and 2013.
My research focuses on scalable, efficient and reliable algorithms and models for machine learning and data science. I am interested in the theory and practice of addressing computational and statistical challenges arising from models involving sparsity, graph or low-rank structures with efficient optimization methods. To this end, I leverage mathematics ranging from high-dimensional probability, applied and computational harmonic analysis, non-convex optimization to numerical linear algebra in my research.
I am also working on novel algorithms for improved payment delivery and capital allocation in payment channel networks such as the Lightning Network, which is a second-layer protocol for the Bitcoin cryptocurrency.
While I am currently not actively seeking to accept new Ph.D. students, I am always willing to consider exceptional candidates. Furthermore, I am always interested in supervising individual research projects and graduation theses with undergraduate and master’s students. For undergraduate students, suitable course-credit based options include ITCS 4750, ITSC 4850, ITSC 4990, ITSC 4991 or the projects I offer at the Office of Undergraduate Research (which are typically paid). For master’s students, suitable research project options include the individual study modules ITCS 6880, ITCS 6881 and ITCS 6882 and the computer science thesis ITCS 6991. Please contact me by email or in person if you are interested.
In Fall 2023, I am teaching a graduate course on Optimization for Machine Learning and Data Science. The targeted audience for this course are master’s and Ph.D. students in computer science, mathematics, data science and electrical engineering. Feel free to reach out for me if you have any questions.
My last name can also be written as Kuemmerle.