Inference via low-dimensional couplings
Name
17-747.pdf
Description
Published version
Size
2.38 MB
Format
Adobe PDF
Checksum (MD5)
ec7a630ae39042f3732dfcff676ea8c4
Author(s)
Spantini, Alessio
Bigoni, Daniele
Marzouk, Youssef M
Date Issued
July 2018
Journal
Journal of machine learning research
Citation
Spantini, Alessio, Daniele Bigoni and Youssef Marzouk. “Inference via low-dimensional couplings.” Journal of machine learning research, vol. 19, 2018, pp. 1-71 © 2018 The Author(s)
Version
Final published version
Abstract
We investigate the low-dimensional structure of deterministic transformations between random variables, i.e., transport maps between probability measures. In the context of statistics and machine learning, these transformations can be used to couple a tractable “reference” measure (e.g., a standard Gaussian) with a target measure of interest. Direct simulation from the desired measure can then be achieved by pushing forward reference samples through the map. Yet characterizing such a map—e.g., representing and evaluating it—grows challenging in high dimensions. The central contribution of this paper is to establish a link between the Markov properties of the target measure and the existence of low-dimensional couplings, induced by transport maps that are sparse and/or decomposable. Our analysis not only facilitates the construction of transformations in high-dimensional settings, but also suggests new inference methodologies for continuous non-Gaussian graphical models. For instance, in the context of nonlinear state-space models, we describe new variational algorithms for filtering, smoothing, and sequential parameter inference. These algorithms can be understood as the natural generalization—to the non-Gaussian case—of the square-root Rauch–Tung–Striebel Gaussian smoother.
MIT Department
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
http://www.jmlr.org/papers/volume19/17-747/17-747.pdf
