We give a new model of learning motivated by smoothed analysis (Spielman and Teng, 2001). In this model, we analyze two new algorithms, for PAC-learning DNFs and agnostically learn...
Adam Tauman Kalai, Alex Samorodnitsky, Shang-Hua T...
—The need to consolidate the information contained in heterogeneous data sources has been widely documented in recent years. In order to accomplish this goal, an organization mus...
Automatic classification of proteins using machine learning is an important problem that has received significant attention in the literature. One feature of this problem is that e...
Arthur Zimek, Fabian Buchwald, Eibe Frank, Stefan ...
We identify data-intensive operations that are common to classifiers and develop a middleware that decomposes and schedules these operations efficiently using a backend SQL databa...
Surajit Chaudhuri, Usama M. Fayyad, Jeff Bernhardt
We investigate the first-order theory of subtyping constraints. We show that the first-order theory of nonstructural subtyping is undecidable, and we show that in the case where a...
Zhendong Su, Alexander Aiken, Joachim Niehren, Tim...