ISBIS - Proximal Hamiltonian Monte Carlo
| Datum | 11 Mar 2026 |
| Tijd | 15:30 CET - 17:00 CET |
| Level of instruction | |
| Instructor |
Dr. Dootika Vats
|
| Registration fee | |
Join us for an engaging webinar organised by the International Society for Business and Industrial Statistics (ISBIS) together with the ISBIS India Interest Group (India IG), exploring new developments in computational statistics and Bayesian methods.
Speaker: Dr. Dootika Vats
Abstract:
Modern Bayesian models often have non-differentiable posteriors. This is a direct consequence of employing a non-differentiable sparsity inducing prior in the model. As a result, sampling even from efficient gradient-based Markov chain Monte Carlo (MCMC) methods becomes difficult. We circumvent this problem by proposing a Proximal Hamiltonian Monte Carlo (p-HMC) algorithm, which uses tools like proximal mappings and Moreau-Yosida (MY) envelopes within Hamiltonian dynamics. A chief contribution of this work is that we also provide conditions for geometric ergodicity of the underlying HMC chain and a methodology to obtain a suitable choice for the regularisation parameter in the MY envelope. We demonstrate the effectiveness of the sampler for a few examples.
Instructors
About the instructor
Dr. Dootika Vats is an Associate Professor in the Department of Mathematics and Statistics at the Indian Institute of Technology, Kanpur. Previously, she was an NSF Postdoctoral fellow with Prof. Gareth Roberts at the University of Warwick. Her PhD was from the University of Minnesota, Twin-Cities working with Prof. Galin Jones. Her research interests are Markov chain Monte Carlo, output analysis for stochastic simulation. Recently, she has been interested in stochastic optimisation algorithms.