Publication: AD Model Builder: using automatic differentiation for statistical inference of highly parameterized complex nonlinear models
Introduction
Applications
Tools
Research Groups
Workshops
Publications
   List Publications
   Advanced Search
   Info
   Add Publications
My Account
About

AD Model Builder: using automatic differentiation for statistical inference of highly parameterized complex nonlinear models

- Article in a journal -
 

Author(s)
David A. Fournier , Hans J. Skaug , Johnoel Ancheta , James Ianelli , Arni Magnusson , Mark N. Maunder , Anders Nielsen , John Sibert

Published in
Optimization Methods and Software

Year
2012

Abstract
Many criteria for statistical parameter estimation, such as maximum likelihood, are formulated as a nonlinear optimization problem. Automatic Differentiation Model Builder (ADMB) is a programming framework based on automatic differentiation, aimed at highly nonlinear models with a large number of parameters. The benefits of using ad are computational efficiency and high numerical accuracy, both crucial in many practical problems. We describe the basic components and the underlying philosophy of ADMB, with an emphasis on functionality found in no other statistical software. One example of such a feature is the generic implementation of Laplace approximation of high-dimensional integrals for use in latent variable models. We also review the literature in which ADMB has been used, and discuss future development of ADMB as an open source project. Overall, the main advantages of ADMB are flexibility, speed, precision, stability and built-in methods to quantify uncertainty.

AD Tools
ad Model Builder'>ad Model Builder

BibTeX
@ARTICLE{
         Fournier2012AMB,
       author = "Fournier, David A. and Skaug, Hans J. and Ancheta, Johnoel and Ianelli, James and
         Magnusson, Arni and Maunder, Mark N. and Nielsen, Anders and Sibert, John",
       title = "{AD} {M}odel {B}uilder: using automatic differentiation for statistical inference of
         highly parameterized complex nonlinear models",
       journal = "Optimization Methods and Software",
       volume = "27",
       number = "2",
       pages = "233--249",
       year = "2012",
       doi = "10.1080/10556788.2011.597854",
       url = "http://www.tandfonline.com/doi/abs/10.1080/10556788.2011.597854",
       eprint = "http://www.tandfonline.com/doi/pdf/10.1080/10556788.2011.597854",
       abstract = "Many criteria for statistical parameter estimation, such as maximum likelihood, are
         formulated as a nonlinear optimization problem. Automatic Differentiation Model Builder (ADMB) is a
         programming framework based on automatic differentiation, aimed at highly nonlinear models with a
         large number of parameters. The benefits of using AD are computational efficiency and high numerical
         accuracy, both crucial in many practical problems. We describe the basic components and the
         underlying philosophy of ADMB, with an emphasis on functionality found in no other statistical
         software. One example of such a feature is the generic implementation of Laplace approximation of
         high-dimensional integrals for use in latent variable models. We also review the literature in which
         ADMB has been used, and discuss future development of ADMB as an open source project. Overall, the
         main advantages of ADMB are flexibility, speed, precision, stability and built-in methods to
         quantify uncertainty.",
       ad_tools = "AD Model Builder"
}


back
  

Contact:
autodiff.org
Username:
Password:
(lost password)