Suyog Gupta
Papers
1
Total Citations
101
H-Index
1
About
Suyog Gupta is a leading researcher in the field of approximate computing, a paradigm that trades precise computation for significant gains in energy efficiency and performance—critical for modern data analytics and cognitive applications. His most-cited work, "Approximate Computing: Challenges and Opportunities" (2016), has garnered over 100 citations and serves as a foundational survey, demonstrating how multiple approximation techniques can be applied to domains that extract deep insights from vast datasets. Gupta’s contributions extend to deep learning and hardware-software co-design, where he has pioneered methods to reduce computational overhead without sacrificing model accuracy. His research has been instrumental in making machine learning more deployable on resource-constrained devices, influencing both academic theory and industrial practice. By systematically identifying the challenges and opportunities in approximation, Gupta has shaped a new generation of energy-efficient computing systems, earning recognition as a key figure in the movement toward sustainable, high-performance AI.
Research Focus
Key Achievements
Top Papers
- 1Approximate computing: Challenges and opportunities101 citations · 2016