我试图以下列方式在R中使用DEoptim
fit <- DEoptim(fn = .obj, lower=lower, upper = upper,
control = list(itermax = 100, trace = 1, parallelType = 1,
steptol = 25, reltol = 1e-9, strategy = 6))
但是，在并行设置中使用DEoptim不会在多次运行中重现结果。使用parallelType = 0串行运行代码时，我没有遇到此问题。我尝试使用clusterSetRNGStream以及使用set.seed的代码在整个群集中设置种子，但这也无济于事。
在尝试并行运行DEoptim时，是否有人遇到过类似的问题。以下是sessionInfo
sessionInfo()
R version 3.2.1 (2015-06-18)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 7 x64 (build 7601) Service Pack 1
locale:
[1] LC_COLLATE=English_United States.1252 LC_CTYPE=English_United States.1252 LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C LC_TIME=English_United States.1252
attached base packages:
[1] grid stats graphics grDevices utils datasets methods base
other attached packages:
[1] mcGlobaloptim_0.1 doSNOW_1.0.12 iterators_1.0.7 foreach_1.4.2 snow_0.3-13 robust_0.4-16 rrcov_1.3-8 robustbase_0.92-5
[9] MASS_7.3-43 fit.models_0.5-10 lattice_0.20-33 DEoptim_2.2-3 Matrix_1.2-2 covmat_0.1 RMTstat_0.3 mvtnorm_1.0-3
loaded via a namespace (and not attached):
[1] Rcpp_0.12.0 vcd_1.4-1 class_7.3-13 zoo_1.7-12
[5] rngWELL_0.10-3 digest_0.6.8 lmtest_0.9-34 VIM_4.3.0
[9] plyr_1.8.3 chron_2.3-47 fBasics_3011.87 lars_1.2
[13] fGarch_3010.82 stats4_3.2.1 pcaPP_1.9-60 e1071_1.6-6
[17] ggplot2_1.0.1 PortfolioAnalytics_1.0.3636 minqa_1.2.4 data.table_1.9.4
[21] SparseM_1.6 car_2.0-25 nloptr_1.0.4 factorAnalytics_2.0.20
[25] proto_0.3-10 splines_3.2.1 randtoolbox_1.16 lme4_1.1-8
[29] CerioliOutlierDetection_1.0.8 stringr_1.0.0 RCurl_1.95-4.7 munsell_0.4.2
[33] numDeriv_2014.2-1 mnormt_1.5-3 mgcv_1.8-7 nnet_7.3-10
[37] gridExtra_2.0.0 codetools_0.2-14 bitops_1.0-6 leaps_2.9
[41] nlme_3.1-121 gtable_0.1.2 magrittr_1.5 scales_0.2.5
[45] PerformanceAnalytics_1.4.3541 stringi_0.5-5 sn_1.2-3 reshape2_1.4.1
[49] sp_1.1-1 timeDate_3012.100 strucchange_1.5-1 lhs_0.10
[53] xts_0.9-7 boot_1.3-17 sandwich_2.3-3 bestglm_0.34
[57] tools_3.2.1 DEoptimR_1.0-3 parallel_3.2.1 pbkrtest_0.4-2
[61] colorspace_1.2-6 cluster_2.0.3 timeSeries_3012.99 corrplot_0.73