BB: An R Package for Solving a Large System of Nonlinear Equations and for Optimizing a High-Dimensional Nonlinear Objective Function

This introduction to the R package BB is a (slightly) modied version of Varadhan and Gilbert (2009), published in the Journal of Statistical Software. We discuss R package BB, in particular, its capabilities for solving a nonlinear system of equations. The function BBsolve in BB can be used for this purpose. We demonstrate the utility of these functions for solving: (a) large systems of nonlinear equations, (b) smooth, nonlinear estimating equations in statistical modeling, and (c) non-smooth estimating equations arising in rank-based regression modeling of censored failure time data. The function BBoptim can be used to solve smooth, box-constrained optimization problems. A main strength of BB is that, due to its low memory and storage requirements, it is ideally suited for solving high-dimensional problems with thousands of variables.

[1]  P. Grambsch,et al.  Prognosis in primary biliary cirrhosis: Model for decision making , 1989, Hepatology.

[2]  Randy L. Haupt,et al.  Appendix I: Test Functions , 2004 .

[3]  Charles J. Geyer,et al.  Computational Methods for Semiparametric Linear Regression with Censored Data , 1992 .

[4]  James M. Ortega,et al.  Iterative solution of nonlinear equations in several variables , 2014, Computer science and applied mathematics.

[5]  Laurence L. George,et al.  The Statistical Analysis of Failure Time Data , 2003, Technometrics.

[6]  José Mario Martínez,et al.  Spectral residual method without gradient information for solving large-scale nonlinear systems of equations , 2006, Math. Comput..

[7]  Hans Bruun Nielsen.  UCTP - Test Problems for Unconstrained Optimization , 2000 .

[8]  José Mario Martínez,et al.  Algorithm 813: SPG—Software for Convex-Constrained Optimization , 2001, TOMS.

[9]  Stephen J. Ganocy.  Numerical Methods for Nonlinear Estimating Equations , 2006, Technometrics.

[10]  Marcos Raydan,et al.  GRADIENT METHOD WITH DYNAMICAL RETARDS FOR LARGE-SCALE OPTIMIZATION PROBLEMS , 2003 .

[11]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[12]  John E. Dennis,et al.  Numerical methods for unconstrained optimization and nonlinear equations , 1983, Prentice Hall series in computational mathematics.

[13]  P. Diggle.  Analysis of Longitudinal Data , 1995 .

[14]  R. Baker Kearfott,et al.  Some tests of generalized bisection , 1987, TOMS.

[15]  Marcos Raydan,et al.  Nonmonotone Spectral Methods for Large-Scale Nonlinear Systems , 2003, Optim. Methods Softw..

[16]  Marcos Raydan,et al.  The Barzilai and Borwein Gradient Method for the Large Scale Unconstrained Minimization Problem , 1997, SIAM J. Optim..

[17]  L. Grippo,et al.  A nonmonotone line search technique for Newton's method , 1986 .

[18]  R. Varadhan,et al.  Simple and Globally Convergent Methods for Accelerating the Convergence of Any EM Algorithm , 2008 .

[19]  J. Borwein,et al.  Two-Point Step Size Gradient Methods , 1988 .

[20]  D. Ruppert,et al.  Transformation and Weighting in Regression , 1988 .

[21]  Z. Ying,et al.  Rank-based inference for the accelerated failure time model , 2003 .

[22]  Roger Fletcher,et al.  On the Barzilai-Borwein Method , 2005 .