Rahul Parhi
Postdoctoral Researcher
Biomedical Imaging Group
Institute of Electrical and Micro Engineering
École Polytechnique Fédérale de Lausanne
Lausanne, Switzerland
rahul@parhi.com
I am currently a postdoctoral researcher with the Biomedical Imaging Group at the École Polytechnique Fédérale de Lausanne (EPFL), where I am supervised by Michael Unser.
I am on the academic job market.
In July 2022, I defended my Ph.D. in Electrical Engineering at the University of Wisconsin–Madison, where I was supervised by Robert D. Nowak. There, my dissertation received the Harold Peterson Outstanding Dissertation Award. During my Ph.D., I was supported by an NSF Graduate Research Fellowship.
I am generally interested in topics that lie at the interface between functional/harmonic analysis and the data sciences. My primary area of investigation is in the development of the mathematical foundations of neural networks and deep learning with the goal of understanding:
- What is the effect of regularization in deep learning?
- What kinds of functions do neural networks learn?
- Why do neural networks seemingly break the curse of dimensionality?
My research uses tools from mathematical signal processing, functional/harmonic analysis, nonparametric statistics, and nonlinear approximation theory to answer these questions.
Other topics/keywords that catch my attention include computed tomography, inverse problems, sparsity, splines, time–frequency analysis, and wavelets.
For more information, you can take a look at some of my papers.
If you would like to know more about me (because I’m such an interesting person), feel free to look at my résumé.