Rishabh Dixit

Indian Institute of Technology Kanpur, Rutgers, The State University of New Jersey

Papers

Total Citations

116

H-Index

About

Rishabh Dixit is a researcher specializing in online learning, distributed optimization, and time-varying convex optimization, with particular expertise in developing efficient algorithms for dynamic, real-world systems. His work addresses the fundamental challenge of solving nondifferentiable optimization problems under computational constraints, making meaningful contributions to fields such as robotics, sensor networks, and subspace tracking. Dixit's most influential contribution, "Online Learning With Inexact Proximal Online Gradient Descent Algorithms" (2019), has garnered 109 citations and introduced low-complexity algorithmic solutions for dynamic optimization problems where solution accuracy improves incrementally over time — a critical consideration in resource-constrained environments. This work established a practical framework for handling the trade-off between computational efficiency and solution quality. Beyond this landmark paper, Dixit has extended his research into distributed settings, exploring how optimization can be performed collaboratively across dynamic, intermittently connected networks — directly applicable to multi-robot systems and sensor arrays engaged in target tracking and parameter estimation. His body of work demonstrates a consistent focus on bridging theoretical optimization guarantees with practical deployment challenges, positioning him as a thoughtful contributor to the intersection of machine learning, signal processing, and networked systems.