Mark A. Davenport
Associate Professor
Center for Signal and Information Processing
Center for Machine Learning
School of Electrical & Computer Engineering
Georgia Institute of Technology
Contact information
CV || Biography || Academic genealogy
I am an Associate Professor in the School of Electrical & Computer Engineering at the Georgia Institute of Technology. I am a member of the Center for Machine Learning and the Center for Signal and Information Processing. My Erdős number is 3, but my Bacon number is 2, which gives me a very respectable Erdős-Bacon number of 5.
My research interests lie in the intersection of the fields of signal processing, high-dimensional statistics, and machine learning. I am particularly interested in the fundamental role that low-dimensional models and optimization play in these fields.
News
- Santhosh Karnik's paper “Fast multitaper spectral estimation” wins Best Student Paper Award at SampTA 2019
- Received the 2019 Presidential Early Career Award for Scientists and Engineers (PECASE)
- Received the 2017 Class of 1940 W. Roane Beard Outstanding Teacher Award
- Awarded the 2017 Sloan Research Fellowship in Mathematics
Selected recent papers
- S. Karnik, J. Romberg, and M. A. Davenport, “Thomson's multitaper method revisited.” Preprint, March 2021.
- N. Ahad and M. A. Davenport, “Semi-supervised sequence classification through change point detection.” in Proc. AAAI Conf. on Artificial Intelligenec (AAAI-21), Online, January 2021.
- A. Xu and M. A. Davenport, “Simultaneous preference and metric learning from paired comparisons.” in Proc. Conf. on Neural Information Processing Systems (NeurIPS), Online, December 2020. Spotlight Presentation
- A. D. McRae, J. Romberg, and M. A. Davenport, “Sample complexity and effective dimension for regression on manifolds.” in Proc. Conf. on Neural Information Processing Systems (NeurIPS), Online, December 2020.
- M. O'Shaughnessy, G. Canal, M. Connor, M. A. Davenport, and C. J. Rozell, “Generative casual explanations of black-box classifiers.” in Proc. Conf. on Neural Information Processing Systems (NeurIPS), Online, December 2020.
- S. Karnik, J. Romberg, and M. A. Davenport, “Improved characterization of the eigenvalue behavior of discrete prolate spheroidal sequences.” Preprint, 2020.
- R. S. Srinivasa, M. A. Davenport, and J. Romberg, “Sample complexity bounds for localized sketching,” in Proc. Int. Conf. on Artificial Intelligence and Statistics (AISTATS), Online, August 2020.
- L. Xu and M. A. Davenport, “Dynamic knowledge embedding and tracing,” in Proc. Educational Data Mining (EDM), Online, July 2020.