Sampling with non-reversible dynamics

Add to your list(s) Download to your calendar using vCal

• Michela Ottobre (Heriot-Watt University)
• Tuesday 18 July 2017, 12:50-13:30
• Seminar Room 1, Newton Institute.

If you have a question about this talk, please contact INI IT.

SIN - Scalable inference; statistical, algorithmic, computational aspects

In recent years the observation that “irreversible processes converge to equilibrium faster than their reversible counterparts” has sparked a significant amount of research to exploit irreversibility within sampling schemes, thereby accelerating convergence of the resulting Markov Chains. It is now understood how to design irreversible continuous-time dynamics with prescribed invariant measure. However, for sampling/simulation purposes, such dynamics still need to undergo discretization and, as it is well known, naive discretizations can completely destroy all the good properties of the continuous-time process.  In this talk we will i) give some background on irreversibility  ii) present some pros and cons of using irreversible proposals within reversible schemes (Joint work with K. Spiliopoulos and N. Pillai).

This talk is part of the Isaac Newton Institute Seminar Series series.

This talk is included in these lists:

• All CMS events
• Featured lists
• INI info aggregator
• Isaac Newton Institute Seminar Series
• School of Physical Sciences
• Seminar Room 1, Newton Institute
• bld31

Note that ex-directory lists are not shown.