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...
We propose a novel semi-supervised classifier for handwritten digit recognition problems that is based on the assumption that any digit can be obtained as a slight transformation...
: We generalize the notion of pattern avoidance to arbitrary functions on ordered sets, and consider specifically three scenarios for permutations: linear, cyclic and hybrid, the f...