We describe a technique for comparing distributions without the need for density estimation as an intermediate step. Our approach relies on mapping the distributions into a reprodu...
Alexander J. Smola, Arthur Gretton, Le Song, Bernh...
In real-world applications, “what you saw” during training is often not “what you get” during deployment: the distribution and even the type and dimensionality of features...
It is well-known that supervised learning techniques such as linear discriminant analysis (LDA) often suffer from the so called small sample size problem when apply to solve face ...
Jie Wang, Konstantinos N. Plataniotis, Anastasios ...
Most accurate predictions are typically obtained by learning machines with complex feature spaces (as e.g. induced by kernels). Unfortunately, such decision rules are hardly access...
We describe the rationale behind the design of key features of Titanium—an explicitly parallel dialect of JavaTM for high-performance scientific programming—and our experienc...
Katherine A. Yelick, Paul N. Hilfinger, Susan L. G...