Skip to main content
. 2018 May 2;34(19):3365–3376. doi: 10.1093/bioinformatics/bty357

Fig. 8.

Fig. 8.

Comparing VT/SIDES/INFO+ in terms of their execution time. For INFO+ we have two versions, one that it returns a full ranking of all biomarkers, and one that it is just returns the top-K most important biomarkers. For all the experiments we simulated data from M-1 with predictive strength θ = 1. (a) Execution time vs sample size. (b) Using INFO+ with various top-K. For (a) we fixed dimensionality p = 30 and we simulate various sample sizes, while for (b) we fixed sample size n = 2000 and we simulate various dimensionalities