Support Vector Machines (SVMs) perform pattern recognition between two point classes by nding a decision surface determined by certain points of the training set, termed Support V...
Nonsmoothness pervades optimization, but the way it typically arises is highly structured. Nonsmooth behavior of an objective function is usually associated, locally, with an activ...
Hardness amplification is the fundamental task of converting a -hard function f : {0, 1}n {0, 1} into a (1/2 - )-hard function Amp(f), where f is -hard if small circuits fail to c...
We consider the problem of semi-supervised feature selection, where we are given a small amount of labeled examples and a large amount of unlabeled examples. Since a small number ...
We consider the problem of finding generalized plans for situations where the number of objects may be unknown and unbounded during planning. The input is a domain specification...
Siddharth Srivastava, Neil Immerman, Shlomo Zilber...