Imagine a No-U-Turn Sampler that can adapt both its path-length and step-size on the fly, responding to the local geometry of the target distribution, while still preserving detailed balance. In … Read More
In a highly cited paper, Diaconis et al, (2000) lifted the symmetric random walk on the discrete circle by adding an auxiliary velocity variable that is flipped in each step … Read More
Anyone who has ever used Hamiltonian Monte Carlo samplers before has probably encountered the so-called tuning problem: in short, it is not at all obvious how to pick the algorithm’s … Read More
Very fortunate to have Bob Carpenter (Flatiron Institute) visiting Rutgers Camden during the week of March 18th. Seminar details are linked here.
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
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
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
Very fortunate to have Sonja Cox (University of Amsterdam) visiting Rutgers Camden during the week of Oct. 16th. Seminar details are linked here.
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.
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.