معرفی
Rajiv Khanna is an Assistant Professor in the Department of Computer Science at Purdue University. His research focuses on machine learning, particularly in optimization, theoretical foundations, and interpretability. Prior to this role, he served as a Visiting Faculty Researcher at Google, a postdoctoral scholar at the Foundations of Data Analytics Institute at UC Berkeley, and a Research Fellow in the Foundations of Data Science program at the Simons Institute, UC Berkeley. He holds a PhD in Electrical and Computer Engineering from the University of Texas at Austin.
His research interests span machine learning subfields including optimization techniques, theoretical analysis, and model interpretability. He has contributed to areas such as loss surface geometry, generalization bounds, and algorithmic fairness. His work emphasizes bridging the gap between theory and practice in machine learning systems.
Dr. Khanna’s academic journey includes postdoctoral research at UC Berkeley and collaborations with industry through his role at Google. His research often explores the computational and statistical trade-offs in modern machine learning models, with a focus on scalable and interpretable solutions.
