AY2024-2025 Sabbatical Leave
Will be taking a sabbatical leave from Rutgers for the academic year 2024-2025. As much as I enjoy teaching, it seems opportune to devote my full effort to research, particularly … Read More
Nawaf Bou-Rabee
4th Italian Meeting on Probability & Mathematical Statistics
Will be speaking at a contributed session organized by Mirko D’Ovidio (Sapienza) with special focus on sticky Brownian motion at the 4th Italian Meeting on Probability and Mathematical Statistics to … Read More
Bernoulli-IMS 11th World Congress in Probability & Statistics
Will be speaking at an invited session organized by Yuansi Chen (Duke) entitled “Recent Advances in Sampling” of the 11th World Congress in Probability and Statistics to be held August … Read More
Sonja Cox Visit & Seminar
Very fortunate to have Sonja Cox (University of Amsterdam) visiting Rutgers Camden during the week of Oct. 16th. Seminar details are linked here.
Randomized Runge-Kutta-Nyström
With Tore Selland Kleppe (Stavanger, Norway), released a preprint presenting 2.5/3.5-order L^2-accurate Randomized Runge-Kutta-Nyström methods to approximate the Hamiltonian flow within unadjusted Hamiltonian Monte Carlo and unadjusted kinetic Langevin chains.
Hamiltonian MCMC for Nonlinear Probability Measures
Together with Katharina Schuh (TU Wien), released a preprint on a nonlinear generalization of Hamiltonian Monte Carlo for sampling from nonlinear probability measures of mean-field type.
Coupling Framework for Metropolis-Adjusted Kernels
Together with Stefan Oberdörster (Bonn), released a preprint presenting a new tool for total variation mixing time analysis of Metropolis-adjusted Markov kernels via couplings without restrictive assumptions on either the … Read More
Randomized Time Integrator for Hamiltonian MCMC
Together with Milo Marsden (Stanford), released a preprint that constructs a randomized time integrator for Hamiltonian MCMC and analyzes the L^2-Wasserstein contractivity and asymptotic bias of the corresponding unadjusted Hamiltonian … Read More