Exact learning of half-spaces over finite subsets of IRn from membership queries is considered. We describe the minimum set of labelled examples separating the target concept from ...
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circui...
We introduce a combinatorial dimension that characterizes the number of queries needed to exactly (or approximately) learn concept classes in various models. Our general dimension...
We study the dynamic membership problem, one of the most fundamental data structure problems, in the cell probe model with an arbitrary cell size. We consider a cell probe model e...
We study two fundamental static data structure problems, membership and perfect hashing, in Yao's cell probe model. The first space and bit probe optimal worst case upper bou...