We further develop the idea that the PAC-Bayes prior can be informed by the data-generating distribution. We prove sharp bounds for an existing framework of Gibbs algorithms, and ...
We examine designs and binary codes associated with the line graph of the n-cube Qn, i.e. the Hamming graph H(n, 2). We find the automorphism groups and the parameters of the cod...
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...
Resource scheduling in large-scale, volatile desktop grids is challenging because resource state is both dynamic and eclectic. Matching available resources with requests is not al...
Deger Cenk Erdil, Michael J. Lewis, Nael B. Abu-Gh...
Background: Extensive and automated data integration in bioinformatics facilitates the construction of large, complex biological networks. However, the challenge lies in the inter...