A new boosting algorithm MadaBoost is proposed that can be casted in the statistical query learning model [Kea93] and thus, it is robust to random classification noise [AL88].Expand

This paper proposes an adaptive sampling algorithm that solves a general problem covering many problems arising in applications of discovery science, and describes how different instantiations of it can be applied to scale up knowledge discovery problems that appear in several areas.Expand

This paper presents an experimental evaluation of a boosting based learning system that can be run efficiently over a large dataset and provides experimental evidence that the method is as accurate as the equivalent algorithm that uses all the dataset but much faster.Expand

An incremental output polynomial time algorithm is given for exact learning both the read-k CNF and (not necessarily read restricted) DNF descriptions of f, the only method of obtaining information about f through membership queries.Expand

Abstract.In this paper, we show how to extend the argument due to Bonet, Pitassi and Raz to show that bounded-depth Frege proofs do not have feasible interpolation, assuming that factoring of Blum… Expand

This paper proposes an adaptive sampling method that solves a general problem covering many actual problems arising in applications of discovery science, and proves the correctness of the method and estimates its efficiency theoretically.Expand

In this paper; we show how to extend the argument due to Bonet, Pitassi and Raz to show that bounded-depth Frege proofs do not have feasible interpolation, assuming that factoring of Blum integers or… Expand

This paper exhibits polynomial time algorithms for testing self-duality for several natural classes of formulas where the problem was not known to be solvable.Expand

This paper shows how the algorithm can be improved by substituting the exploration phase, that builds a model of the underlying Markov decision process by estimating the transition probabilities, by an adaptive sampling method more suitable for the problem.Expand

This paper presents two on-line sampling algorithms for selecting a hypothesis, gives theoretical bounds on the number of examples needed, and analyses them experimentally to study the problem of how to determine which of the hypotheses in the class is almost the best one.Expand