Rahul Parhi

rahul [at] ucsd [dot] edu
Assistant Professor of ECE at UCSD

rahul/rahul-epfl-bm-2023.jpg

6406 Jacobs Hall

9500 Gilman Dr, MC 0407

La Jolla, CA 92093

I am an assistant professor of electrical and computer engineering (ECE) at the University of California, San Diego (UCSD), which I joined in 2024. Previously, I was a postdoctoral researcher at the École Polytechnique Fédérale de Lausanne (EPFL) from 2022 to 2024, where I worked with Michael Unser. I obtained my Ph.D. in 2022 at the University of Wisconsin–Madison (UW–Madison), where I was supervised by Robert D. Nowak. I completed my undergraduate studies at the University of Minnesota, Twin Cities (UMN) in 2018.

★ I am actively recruiting Ph.D. students to begin in Fall 2025 as well as postdocs who are generally interested in the mathematics of data science. If you are interested in working with me, please send me an email with (i) your CV and (ii) a list of topics you are interested in.

My research lies at the interface between functional/harmonic analysis, signal processing, machine learning, and nonparametric statistics. I am primarily interested in the mathematics of data science with a particular focus on the foundations of neural networks and deep learning. Some questions my research aims to answer include:

  1. What is the effect of regularization in deep learning?
  2. What kinds of functions do neural networks learn?
  3. Why do neural networks seemingly break the curse of dimensionality?

Other topics/keywords that catch my attention include computed tomography, geometry of Banach spaces, inverse problems, sparsity, splines, time–frequency analysis, and wavelets. For more information, you can take a look at my papers.

news

Sep 07, 2024 I have finished moving to San Diego from Lausanne.
Apr 08, 2024 I have accepted a job offer from the ECE department at UCSD.

selected publications

  1. Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
    Joseph ShenoudaRahul ParhiKangwook Lee, and Robert D. Nowak
    Journal of Machine Learning Research, 2024
  2. Distributional Extension and Invertibility of the k-Plane Transform and Its Dual
    Rahul Parhi, and Michael Unser
    SIAM Journal on Mathematical Analysis, 2024
  3. Deep Learning Meets Sparse Regularization: A signal processing perspective
    Rahul Parhi, and Robert D. Nowak
    IEEE Signal Processing Magazine, 2023
  4. The Sparsity of Cycle Spinning for Wavelet-Based Solutions of Linear Inverse Problems
    Rahul Parhi, and Michael Unser
    IEEE Signal Processing Letters, 2023
  5. Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks
    Rahul Parhi, and Robert D. Nowak
    IEEE Transactions on Information Theory, 2023