skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Kullback--Leibler Approximation for Probability Measures on Infinite Dimensional Spaces

Abstract

In a variety of applications it is important to extract information from a probability measure μ on an infinite dimensional space. Examples include the Bayesian approach to inverse problems and (possibly conditioned) continuous time Markov processes. It may then be of interest to find a measure ν, from within a simple class of measures, which approximates μ. Here, this problem is studied in the case where the Kullback–Leibler divergence is employed to measure the quality of the approximation. A calculus of variations viewpoint is adopted, and the particular case where ν is chosen from the set of Gaussian measures is studied in detail. Basic existence and uniqueness theorems are established, together with properties of minimizing sequences. Furthermore, parameterization of the class of Gaussians through the mean and inverse covariance is introduced, the need for regularization is explained, and a regularized minimization is studied in detail. The calculus of variations framework resulting from this work provides the appropriate underpinning for computational algorithms.

Authors:
 [1];  [2];  [3];  [3]
  1. Univ. of Cincinnati, OH (United States). Dept. of Physics
  2. Drexel Univ., Philadelphia, PA (United States). Dept. of Mathematics
  3. Warwick Univ., Coventry (United Kingdom). Mathematics Inst.
Publication Date:
Research Org.:
Warwick Univ., Coventry (United Kingdom)
Sponsoring Org.:
USDOE Office of Science (SC); European Research Council (ERC); Engineering and Physical Sciences Research Council (EPSRC); US Department of the Navy, Office of Naval Research (ONR); National Science Foundation (NSF)
OSTI Identifier:
1459163
Grant/Contract Number:  
SC0002085; OISE-0967140
Resource Type:
Accepted Manuscript
Journal Name:
SIAM Journal of Mathematical Analysis
Additional Journal Information:
Journal Volume: 47; Journal Issue: 6; Journal ID: ISSN 0036-1410
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Kullback–Leibler divergence; relative entropy; Gaussian measures

Citation Formats

Pinski, Frank J., Simpson, G., Stuart, A. M., and Weber, Hendrik. Kullback--Leibler Approximation for Probability Measures on Infinite Dimensional Spaces. United States: N. p., 2015. Web. https://doi.org/10.1137/140962802.
Pinski, Frank J., Simpson, G., Stuart, A. M., & Weber, Hendrik. Kullback--Leibler Approximation for Probability Measures on Infinite Dimensional Spaces. United States. https://doi.org/10.1137/140962802
Pinski, Frank J., Simpson, G., Stuart, A. M., and Weber, Hendrik. Thu . "Kullback--Leibler Approximation for Probability Measures on Infinite Dimensional Spaces". United States. https://doi.org/10.1137/140962802. https://www.osti.gov/servlets/purl/1459163.
@article{osti_1459163,
title = {Kullback--Leibler Approximation for Probability Measures on Infinite Dimensional Spaces},
author = {Pinski, Frank J. and Simpson, G. and Stuart, A. M. and Weber, Hendrik},
abstractNote = {In a variety of applications it is important to extract information from a probability measure μ on an infinite dimensional space. Examples include the Bayesian approach to inverse problems and (possibly conditioned) continuous time Markov processes. It may then be of interest to find a measure ν, from within a simple class of measures, which approximates μ. Here, this problem is studied in the case where the Kullback–Leibler divergence is employed to measure the quality of the approximation. A calculus of variations viewpoint is adopted, and the particular case where ν is chosen from the set of Gaussian measures is studied in detail. Basic existence and uniqueness theorems are established, together with properties of minimizing sequences. Furthermore, parameterization of the class of Gaussians through the mean and inverse covariance is introduced, the need for regularization is explained, and a regularized minimization is studied in detail. The calculus of variations framework resulting from this work provides the appropriate underpinning for computational algorithms.},
doi = {10.1137/140962802},
journal = {SIAM Journal of Mathematical Analysis},
number = 6,
volume = 47,
place = {United States},
year = {2015},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 12 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

A numerical method for detecting singular minimizers
journal, March 1987

  • Ball, J. M.; Knowles, G.
  • Numerische Mathematik, Vol. 51, Issue 2
  • DOI: 10.1007/BF01396748

Bayesian inverse problems for functions and applications to fluid mechanics
journal, October 2009


$I$-Divergence Geometry of Probability Distributions and Minimization Problems
journal, February 1975


MAP estimators and their consistency in Bayesian nonparametric inverse problems
journal, September 2013


Uncertainty Quantification and Weak Approximation of an Elliptic Inverse Problem
journal, January 2011

  • Dashti, M.; Stuart, A. M.
  • SIAM Journal on Numerical Analysis, Vol. 49, Issue 6
  • DOI: 10.1137/100814664

Monge-Kantorovitch Measure Transportation and Monge-Amp�re Equation on Wiener Space
journal, March 2004


Quantifying the Predictive Skill in Long-Range Forecasting. Part I: Coarse-Grained Predictions in a Simple Ocean Model
journal, March 2012


Information-theoretic tools for parametrized coarse-graining of non-equilibrium extended systems
journal, August 2013

  • Katsoulakis, Markos A.; Plecháč, Petr
  • The Journal of Chemical Physics, Vol. 139, Issue 7
  • DOI: 10.1063/1.4818534

Coarse-graining schemes and a posteriori error estimates for stochastic lattice systems
journal, May 2007

  • Katsoulakis, Markos A.; Plecháč, Petr; Rey-Bellet, Luc
  • ESAIM: Mathematical Modelling and Numerical Analysis, Vol. 41, Issue 3
  • DOI: 10.1051/m2an:2007032

A Convexity Principle for Interacting Gases
journal, June 1997


Γ-Limit for Transition Paths of Maximal Probability
journal, February 2012


Posterior consistency via precision operators for Bayesian nonparametric drift estimation in SDEs
journal, February 2013

  • Pokern, Y.; Stuart, A. M.; van Zanten, J. H.
  • Stochastic Processes and their Applications, Vol. 123, Issue 2
  • DOI: 10.1016/j.spa.2012.08.010

Inverse problems: A Bayesian perspective
journal, May 2010


    Works referencing / citing this record:

    A Generalized Relative (α, β)-Entropy: Geometric Properties and Applications to Robust Statistical Inference
    journal, May 2018


    Computationally Efficient Variational Approximations for Bayesian Inverse Problems
    journal, July 2016

    • Tsilifis, Panagiotis; Bilionis, Ilias; Katsounaros, Ioannis
    • Journal of Verification, Validation and Uncertainty Quantification, Vol. 1, Issue 3
    • DOI: 10.1115/1.4034102