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
Areas of Expertise:
- Coding Theory & Lattices
- Sparse Recovery
- Sublinear algorithms
- Foundations of Machine Learning
Venkata’s research focuses on the algorithmic aspects of computing with structured data and their applications in various domains such as communication, data storage, health care, and collaborative learning. His research mainly aims to identify an underlying structure in the data that can be leveraged to design efficient algorithms for certain computational tasks. When the data is devoid of any favorable structure, we aim to embed one to facilitate computations. In the process, we use tools and develop techniques from several areas of mathematics and computer science like optimization, coding theory, high-dimensional geometry, the geometry of numbers, sublinear-time algorithms, and differential privacy.
Honors and Awards:
- SOURCE 2022 — Research Assistant Grant to support undergraduate student involvement in research.
- CUSE Seed Grant 2021.
Selected Publications:
- vqSGD: Vector Quantized Stochastic Gradient Descent, Venkata Gandikota, Daniel Kane, Raj K. Maity, Arya Mazumdar. IEEE Transactions on Information Theory, 2022.
- Support Recovery of Sparse Signals from a Mixture of Linear Measurements, Venkata Gandikota, Arya Mazumdar, Soumyabrata Pal. Advances in Neural Information Processing Systems (NeurIPS), 2021.
- Recovery of Sparse Linear Classifiers from Mixture of Responses, Venkata Gandikota, Arya Mazumdar, Soumyabrata Pal. 34th Conference on Neural Information Processing Systems (NeurIPS), 2020.
- Reliable Distributed Clustering with Redundant Data Assignment, Venkata Gandikota, Arya Mazumdar, Ankit Rawat. IEEE Symposium on Information Theory (ISIT), 2020.
- Nearly Optimal Sparse Group Testing, Venkata Gandikota, Elena Grigorescu, Sidharth Jaggi, Samson Zhou. IEEE Transactions on Information Theory, 2019.