Bootstrap Inference for Network Construction

Details Bootstrap Inference for Network Construction Bootstrap Inference for Network Construction

2011-11-21

arxiv.org/abs/1111.5028v1

Statistics

Methodology

Scientific paper

Regularization techniques are widely used for tackling high-dimension-low-sample-size problems. Yet, finding the right amount of regularization can be challenging, especially in the unsupervised setting such as structure learning problems where traditional methods such as BIC or cross-validation often do not work well. In this paper, we propose a new method --- Bootstrap Inference for Network COnstruction (BINCO) --- to infer networks by directly controlling the false discovery rates (FDRs) of the selected edges. This method utilizes the idea of model aggregation. It fits a mixture model for the distribution of edge selection frequencies to estimate the FDRs. As this method only depends on selection frequencies, it is applicable to a wide range of applications beyond network construction.

Affiliated with

Also associated with

No associations

Rating

Bootstrap Inference for Network Construction does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Bootstrap Inference for Network Construction, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Bootstrap Inference for Network Construction will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-551396