Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Langevin-based Strategy for Efficient Proposal Adaptation in Population Monte Carlo

Abstract: 

Population Monte Carlo (PMC) algorithms are a family of
adaptive importance sampling (AIS) methods for approximating
integrals in Bayesian inference. In this paper, we propose
a novel PMC algorithm that combines recent advances
in the AIS and the optimization literatures. In such a way, the
proposal densities are adapted according to the past weighted
samples via a local resampling that preserves the diversity,
but we also exploit the geometry of the targeted distribution.
A scaled Langevin strategy with Newton-based scaling metric
is retained for this purpose, allowing to adapt jointly the
means and the covariances of the proposals, without needing
to tune any extra parameter. The performance of the proposed
technique is clearly superior in two numerical examples at the
cost of a reasonable computational complexity increment.

up
0 users have voted:

Paper Details

Authors:
Submitted On:
8 May 2019 - 8:22am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Emilie Chouzenoux
Paper Code:
SPTM-P2.10
Document Year:
2019
Cite

Document Files

poster_ICASSP_2019.pdf

(28)

Subscribe

[1] , "Langevin-based Strategy for Efficient Proposal Adaptation in Population Monte Carlo", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4085. Accessed: Dec. 08, 2019.
@article{4085-19,
url = {http://sigport.org/4085},
author = { },
publisher = {IEEE SigPort},
title = {Langevin-based Strategy for Efficient Proposal Adaptation in Population Monte Carlo},
year = {2019} }
TY - EJOUR
T1 - Langevin-based Strategy for Efficient Proposal Adaptation in Population Monte Carlo
AU -
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4085
ER -
. (2019). Langevin-based Strategy for Efficient Proposal Adaptation in Population Monte Carlo. IEEE SigPort. http://sigport.org/4085
, 2019. Langevin-based Strategy for Efficient Proposal Adaptation in Population Monte Carlo. Available at: http://sigport.org/4085.
. (2019). "Langevin-based Strategy for Efficient Proposal Adaptation in Population Monte Carlo." Web.
1. . Langevin-based Strategy for Efficient Proposal Adaptation in Population Monte Carlo [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4085