We tried LASSO prior to this work, but the results

We appreciate the praise for the "Extremely good and unique empirical Lasso or Markov Blanket (MB) requires causal sufficiency, let alone curse of dimensionality. In sparse large graphs FS gives more FP . BE performs worse in small sparse graphs. BE and FS computations took significantly long. Indeed, an empirical example of this was given in section A2, Figure 1 of suppl.