A semi-supervised framework that incorporates labeled and unlabeled data in a general-purpose learner is proposed and properties of reproducing kernel Hilbert spaces are used to prove new Representer theorems that provide theoretical basis for the algorithms.
This paper constructs a family of data-dependent norms on Reproducing Kernel Hilbert Spaces (RKHS) that allow the structure of the RKHS to reflect the underlying geometry of the data.
A semi-supervised framework that incorporates labeled and unlabeled data in a general-purpose learner is focused on and properties of Reproducing Kernel Hilbert spaces are utilized to prove new Representer theorems that provide theoretical basis for the algorithms.
The performance and behavior of various S3VMs algorithms is studied together, under a common experimental setting, to review key ideas in this literature on semi-supervised support Vector Machines.
This paper proposes SystemML in which ML algorithms are expressed in a higher-level language and are compiled and executed in a MapReduce environment and describes and empirically evaluate a number of optimization strategies for efficiently executing these algorithms on Hadoop, an open-source mapReduce implementation.
An implementation of Transductive SVM (TSVM) that is significantly more efficient and scalable than currently used dual techniques, for linear classification problems involving large, sparse datasets, and a variant of TSVM that involves multiple switching of labels.
This paper proposes a Co-Regularization framework where classifiers are learnt in each view through forms of multi-view regularization, and proposes algorithms within this framework that are based on optimizing measures of agreement and smoothness over labeled and unlabeled examples.
A semisupervised framework that incorporates labeled and unlabeled data in a generalpurpose learner and gives rise to a regularized form of spectral clustering with an out-of-sample extension is proposed.
A new discrepancy measure called box discrepancy is derived based on theoretical characterizations of the integration error with respect to a given sequence based on explicit box discrepancy minimization in Quasi-Monte Carlo (QMC) approximations.
This paper reformulates the separable NMF problem as that of finding the extreme rays of the conical hull of a finite set of vectors and derives new separableNMF algorithms that are highly scalable and empirically noise robust, and have several other favorable properties in relation to existing methods.