Agniva Chowdhury

I am a Postdoctoral Associate in the Department of Computer Science at Rice University, working with Prof. Anshumali Shrivastava. Previously, I was an AI Research Scientist at Intel Corporation and a Postdoctoral Research Associate in the Computer Science and Mathematics Division at Oak Ridge National Laboratory. I received my Ph.D. in Statistics from Purdue University, where I was advised by Prof. Petros Drineas and Prof. Hao Zhang.

My research focuses on randomized numerical linear algebra, scalable optimization, and efficient algorithms for large-scale machine learning and scientific computing. I design sketching-based methods to accelerate large-scale statistical and more general linear algebraic problems with provable guarantees. More recently, I have been working on scalable attention mechanisms and efficient long-context training and inference algorithms for large language models.