Search Results for author: Karsten M. Borgwardt

Found 4 papers, 0 papers with code

Fast and Memory-Efficient Significant Pattern Mining via Permutation Testing

no code implementations15 Feb 2015 Felipe Llinares López, Mahito Sugiyama, Laetitia Papaxanthos, Karsten M. Borgwardt

Westfall-Young light opens the door to significant pattern mining on large datasets that previously led to prohibitive runtime or memory costs.

Two-sample testing

Identifying Higher-order Combinations of Binary Features

no code implementations4 Jul 2014 Felipe Llinares, Mahito Sugiyama, Karsten M. Borgwardt

Finding statistically significant interactions between binary variables is computationally and statistically challenging in high-dimensional settings, due to the combinatorial explosion in the number of hypotheses.

Significant Subgraph Mining with Multiple Testing Correction

no code implementations1 Jul 2014 Mahito Sugiyama, Felipe Llinares López, Niklas Kasenburg, Karsten M. Borgwardt

An open question, however, is whether this strategy of excluding untestable hypotheses also leads to greater statistical power in subgraph mining, in which the number of hypotheses is much larger than in itemset mining.

Two-sample testing

Efficient network-guided multi-locus association mapping with graph cuts

no code implementations10 Nov 2012 Chloé-Agathe Azencott, Dominik Grimm, Mahito Sugiyama, Yoshinobu Kawahara, Karsten M. Borgwardt

We present SConES, a new efficient method to discover sets of genetic loci that are maximally associated with a phenotype, while being connected in an underlying network.

Cannot find the paper you are looking for? You can Submit a new open access paper.