Working on Privacy Preserving Deep Learning using:
- Encrypted Computation on GPUs
- Federated Learning
- Remote Execution (Model Compression)
Vinu’s research focuses on optimizing deep neural network based systems for performance and scalability. More broadly, His research is at the intersection of systems, programming languages and machine learning, to create a more efficient, performant, secure, privacy-preserving and correct software. His PhD research has been mainly focused on deep neural network compression for resource efficient inference and robustness. He is generously supported by a NVIDIA PhD fellowship, mentored by Saurav Muralidharan and Michael Garland, He developed Condensa: A Programming System for Model Compression and Optimization. He has considerable experience constructing tools capable of leveraging the power of GPUs for machine learning computing. He is also interested in applying machine learning to challenging problems within programming systems.
Vinu received his Ph.D. in Computer Science at the School of Computing at the University of Utah, Salt Lake City, working on efficient deep learning computing, robustness and security of deep learning algorithms, advised by Prof. Ganesh Gopalakrishnan. He is one of the five recipients of the NVIDIA Graduate fellowship, the recipients were selected based on their academic achievements and area of research. Prior to graduate studies, Vinu worked at ARM Inc. During his tenure at ARM, he was a recipient of the Bravo award for developing the programmer’s model for verifying real-time (‘R’) profile architecture which provides high-performing processors for safety-critical environments.
Vinu received his bachelor’s degree at the Department of Electronics and Communication Engineering from CMR Institute of Technology, Bangalore, affiliated to the Visvesvaraya Technological University and his Undergraduate research was on efficient double-precision floating point arithmetic on FPGAs at National Aerospace Laboratory, India.
In his spare time, He has committed to mentor the next generation of CS/AI researchers, helping bright undergraduates in STEM (School of Computing) bootstrap their research careers,