I am broadly interested in probability theory, stochastic processes, and their applications in machine learning and AI.

A focus area of my research is the design and analysis of MCMC algorithms. During my Ph.D., I have analyzed non-reversible and Hamiltonian Monte-Carlo Markov chains. I have a keen interest in designing Markov chains that converge faster than the state of the art, especially for state spaces that grow exponentially. I like using elegant coupling techniques, Fourier-transform based methods for the analysis of rate of convergence of these algorithms.

Currently, I am interested in developing faster algorithms used for inferencing from complex probability distributions in AI. I am also eager to explore analysis of other mathematical and statistical methods used in data science.