Â鶹´«Ã½

Rahul Parhi's research lies at the interface between functional/harmonic analysis, signal processing, machine learning, and nonparametric statistics. His primary area of investigation is in the mathematics of data science with a particular focus on the foundations of neural networks and deep learning. Some questions his research aims to answer include:

- 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?

He is also interested in inverse problems, sparsity/compressed sensing, the mathematics of computed tomography, and the geometry of Banach spaces.

Capsule Bio:

Rahul Parhi joined the Department of Electrical and Computer Engineering at Â鶹´«Ã½ in 2024. Prior to that, he was a postdoctoral researcher at the École Polytechnique Fédérale de Lausanne (EPFL) from 2022 to 2024. He received his Ph.D. in electrical engineering from the University of Wisconsin–Madison in 2022. His work lies at the interface between functional and harmonic analysis, signal processing, machine learning, and nonparametric statistics. He is primarily interested in the mathematics of data science with a particular emphasis on the foundations of neural networks and deep learning.

Selected Publications: