Abstract. A formula ψ(Y ) is a selector for a formula ϕ(Y ) in a structure M if there exists a unique Y that satisfies ψ in M and this Y also satisfies ϕ. A formula ψ(X, Y )...
We define notions of stability for learning algorithms and show how to use these notions to derive generalization error bounds based on the empirical error and the leave-one-out e...
We study the problem of fairly dividing a set of goods amongst a group of agents, when those agents have preferences that are ordinal relations over alternative bundles of goods (r...
Abstract. We derive upper and lower bounds for some statistical estimation problems. The upper bounds are established for the Gibbs algorithm. The lower bounds, applicable for all ...
Many practitioners who use EM and related algorithms complain that they are sometimes slow. When does this happen, and what can be done about it? In this paper, we study the gener...
Ruslan Salakhutdinov, Sam T. Roweis, Zoubin Ghahra...