Assistant Professor
Electrical Engineering and Computer Science
CST 4-206B
vsgandik@syr.edu
315 443-6182
Degrees:
- Ph.D. Computer Science – Purdue University
- MS Computer Science – Purdue University
- MSc Mathematics – Birla Institute of Technology and Science, Goa, India
- B.E. Computer Science – Birla Institute of Technology and Science, Goa, India
Lab/ Center/ Institute affiliation:
- Affiliate Faculty, EnCORE Institute (https://encore.ucsd.edu/)
Areas of Expertise:
- Foundations of Data Science
- Coding & Information Theory
- Lattice Algorithms
Dr. Gandikota’s research delves into the algorithmic principles of data recovery from noise, with an emphasis on its applications in fundamental machine learning problems. His primary objective is to delineate the conditions that enable successful data recovery while also devising efficient algorithms to achieve it.
Honors and Awards:
- IEEE Senior Member
- SOURCE RA Grant.
- CUSE Seed Grant.
Selected Publications:
- Combinatorial Group Testing in Presence of Deletions, V Gandikota, N Polyanskii, H Yang. arXiv preprint arXiv:2310.09613
- vqsgd: Vector quantized stochastic gradient descent, V Gandikota, D Kane, RK Maity, A Mazumdar. IEEE Transactions on Information Theory 68 (7), 4573-4587
- Support recovery of sparse signals from a mixture of linear measurements, S Pal, A Mazumdar, V Gandikota. Advances in Neural Information Processing Systems 34, 19082-19094
- Nearly optimal sparse group testing, V Gandikota, E Grigorescu, S Jaggi, S Zhou. IEEE Transactions on Information Theory 65 (5), 2760-2773
- NP-Hardness of Reed–Solomon Decoding, and the Prouhet–Tarry–Escott Problem, V Gandikota, B Ghazi, E Grigorescu. SIAM Journal on Computing, 2018