论文信息 - A Note on Parallelizing the Parameterized Expectations Algorithm

A Note on Parallelizing the Parameterized Expectations Algorithm

The parameterized expectations algorithm (PEA) involves a long simulationand a nonlinear least squares (NLS) fit, both embedded in a loop. Both steps are natural candidates for parallelization.This note shows that parallelization can lead to important speedups forthe PEA.I provide example code for a simple model that can serve as a templatefor parallelization of more interesting models, as well as a download linkfor an image of a bootable CD that allows creation of a cluster and executionof the example code in minutes, with no need to install any software.

Michael Creel

[1] Serguei Maliar,et al. Parameterized Expectations Algorithm and the Moving Bounds , 2003 .

[2] David A. Marshall,et al. Solving nonlinear rational expectations models by parameterized expectations: Convergence to stationary solutions , 1994 .

[3] Lawrence J. Christiano,et al. Algorithms for solving dynamic models with occasionally binding constraints , 1997 .

[4] Michael Creel,et al. User-Friendly Parallel Computations with Econometric Examples , 2005 .

[5] G. Amdhal,et al. Validity of the single processor approach to achieving large scale computing capabilities , 1967, AFIPS '67 (Spring).

[6] Mancia Anguita,et al. MPI Toolbox for Octave , 2001 .