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

• Published in: Optimization methods & software Vol. 27; no. 2; pp. 233 - 249
• Main Authors: Fournier, David A., Skaug, Hans J., Ancheta, Johnoel, Ianelli, James, Magnusson, Arni, Maunder, Mark N., Nielsen, Anders, Sibert, John
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 01.04.2012; Taylor & Francis Ltd
• Subjects: ADMB; automatic differentiation; Laplace approximation; Monte Carlo simulation; Optimization; Parameter estimation; separability; Studies
• ISSN: 1055-6788; 1026-7670; 1029-4937; 1029-4937
• DOI: 10.1080/10556788.2011.597854

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.