kernlab - Invalid probability model for large support vector machines using ksvm in R -

i train support vector machines using ksvm function kernlab package in r, on large numbers of observations (300k) not many features (1-8). want use resulting probability model, large data sets, resulting probability model has unexpected format.

this should happen:

n <- 1000 df <- data.frame(label=c(rep("x",n),rep("y",n)),value=c(runif(n),runif(n)+2)) m <- ksvm(label~value,df,prob.model=true)  > prob.model(m) [[1]] [[1]]$a [1] -6.836228  [[1]]$b [1] 0.003163229 

however, large values of n (e.g. 100k; beware of high memory usage , long execution times), value of prob.model(m)[[1]] numeric vector of length 2n, seemingly likelihood each observation in df. cause this?

session info:

r version 2.15.2 (2012-10-26) platform: x86_64-unknown-linux-gnu (64-bit)  locale:  [1] lc_ctype=en_us.utf-8       lc_numeric=c               lc_time=en_us.utf-8        lc_collate=en_us.utf-8     lc_monetary=en_us.utf-8    lc_messages=en_us.utf-8    lc_paper=c                 lc_name=c                  lc_address=c [10] lc_telephone=c             lc_measurement=en_us.utf-8 lc_identification=c  attached base packages: [1] graphics  grdevices datasets  utils     stats     methods   base  other attached packages: [1] kernlab_0.9-16   e1071_1.6-1      class_7.3-5      data.table_1.8.8  loaded via namespace (and not attached): [1] tools_2.15.2 

edit: classification task i'm talking about, df has following form:

label value "x"    0.21 ... "x"   -1.20 "y"    2.42 ... 

the origin of problem indicated following error message:

line search fails 

a more specific question, including original data frame used, here: line search fails in training ksvm prob.model.