Sanketh Vedula

PhD Candidate, Technion

sanketh-bio.jpg

Taub 534

The Computer Science Department, Technion

Haifa, Israel 32000

I’m a PhD student at the Computer Science Department, Technion – Israel Institute of Technology advised by Prof. Alex Bronstein.

I work on problems in robust and reliable machine learning, geometric deep learning, and computational imaging. I am broadly interested in anything involving statistics, optimization, machine learning, and their scientific applications.

I aspire to build solutions for challenging problems that have real-world impact. I enjoy doing research, learning, and discussing ideas with people.

In parallel to my MSc and PhD studies, I worked as a Data Scientist at Sibylla Ltd. (a seed funded startup, Technion spin-off) building mid-frequency quant-trading and portfolio management strategies.

I received an M.Sc. (cum laude) in Computer Science from Technion in 2020, where I was advised by Prof. Alex Bronstein and Dr. Michael Zibulevsky. During my masters’ research, we proposed efficient learning-based designs for different imaging systems. Earlier, I obtained a B.Eng. (Hons.) in Computer Science from BITS Pilani in 2017.

selected publications

  1. ICML Workshop
    Continuous Vector Quantile Regression
    Vedula, S., Tallini, I., Rosenberg, A., Pegoraro, M., Rodola, E., Romano, Y., and Bronstein, A.
    In ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems 2023
  2. ICML Workshop
    Vector Quantile Regression on Manifolds
    Pegoraro, M.,  Vedula, S., Rosenberg, A., Tallini, I., Rodola, E., and Bronstein, A.
    In ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems 2023
  3. MSML
    Spectral Geometric Matrix Completion
    Boyarski, A.,  Vedula, S., and Bronstein, A.
    In Proceedings of the Second Mathematical and Scientific Machine Learning Conference (MSML), 2021
  4. ICLR
    Fast Nonlinear Vector Quantile Regression
    Rosenberg, A.,  Vedula, S., Romano, Y., and Bronstein, A.
    In Proc. International Conference on Learning Representations (ICLR), 2023