Rahul Parhi

Rahul Parhi is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of California, San Diego. His research focuses on the mathematics of data science, with an emphasis on the foundations of neural networks and deep learning. He investigates questions related to regularization in deep learning, the functions learned by neural networks, and the apparent ability of neural networks to break the curse of dimensionality. His work also spans inverse problems, sparsity, compressed sensing, computed tomography, and the geometry of Banach spaces. Parhi joined UC San Diego in 2024 after serving as a postdoctoral researcher at École Polytechnique Fédérale de Lausanne from 2022 to 2024. He earned his Ph.D. in electrical engineering from the University of Wisconsin–Madison in 2022.

Rahul Parhi is a researcher at the University of California, San Diego, focusing on applied harmonic analysis, mathematics of data, signal processing, machine learning, and statistics. His work explores the interplay between neural networks and signal processing, particularly in the context of sparse regularization and variational spline theory. He investigates the mathematical foundations of deep learning, including the role of activation functions and the properties of neural network solutions. His research also addresses inverse problems, approximation theory, and the optimization of neural architectures. Parhi's contributions span both theoretical and applied aspects of data science, with an emphasis on understanding the statistical and functional properties of learning algorithms.