Loading Events

« All Events

  • This event has passed.

Pierre NYQUIST (Eindhoven University of Technology) – “The Infinite Swapping Algorithm: Properties and Applications.”

October 1, 3:30 pm - 4:30 pm

1st Monday of each month

Time: 3:30 pm – 4:30 pm
Date: 01 th of Octobre 2018
Place: Room 3105

Pierre NYQUIST (Eindhoven University of Technology) – “The Infinite Swapping Algorithm: Properties and Applications.”

Abstract : Infinite swapping is a Monte Carlo method originally developed by Doll, Dupuis and co-authors using empirical measure large deviations. The method is designed to overcome the problem of rare-event sampling, and thus speed up convergence, in the setting of computing integrals with respect to Gibbs measures. In our subsequent work the properties of infinite swapping were studied further using a combination of empirical measure large deviations and stochastic ergodic control problems, revealing explicit information on the convergence properties of the sampling scheme.

This talk will focus on the properties of infinite swapping, and the associated large deviations analysis, and (non-standard) applications in quantum dynamics and machine learning. Given time we will also discuss briefly the use of empirical measure large deviations to study convergence rates for MCMC methods, and possible implications of the comparison between parallel tempering and infinite swapping for training RBMs.

This is based on joint work with Paul Dupuis, Jim Doll (Brown University), Henrik Hult and Carl Ringqvist (KTH).

 

 

Details

Date:
October 1
Time:
3:30 pm - 4:30 pm
Event Categories:
,

Organizers

Caroline HILLAIRET
Peter TANKOV