In this paper we analyze the PAC learning abilities of several simple iterative algorithms for learning linear threshold functions, obtaining both positive and negative results. W...
We address the problem of evaluating the risk of a given model accurately at minimal labeling costs. This problem occurs in situations in which risk estimates cannot be obtained f...
Christoph Sawade, Niels Landwehr, Steffen Bickel, ...
In this study, we consider an environment composed of a heterogeneous cluster of multicore-based machines used to analyze satellite images. The workload involves large data sets, a...
Luis D. Briceo, Jay Smith, Howard Jay Siegel, Anth...
We consider the problem of learning sparse parities in the presence of noise. For learning parities on r out of n variables, we give an algorithm that runs in time poly log 1 δ , ...
This paper is a report on experiences in benchmarking I/O performance on leading computational facilities on the NSF TeraGrid network with a large scale scientific application. In...