This paper analyzes the potential advantages and theoretical challenges of “active learning” algorithms. Active learning involves sequential sampling procedures that use infor...
Abstract. We establish a generic theoretical tool to construct probabilistic bounds for algorithms where the output is a subset of objects from an initial pool of candidates (or mo...
— Simulated Evolution (SimE) is a sound stochastic approximation algorithm based on the principles of adaptation. If properly engineered it is possible for SimE to reach nearopti...
Abstract. We consider the problem of computing tractable approximations to CNF formulas, extending the approach of Selman and Kautz to compute the Horn-LUB to involve renaming of v...
In this paper we consider problems related to the sortedness of a data stream. First we investigate the problem of estimating the distance to monotonicity; given a sequence of len...