We show that forms of Bayesian and MDL inference that are often applied to classification problems can be inconsistent. This means that there exists a learning problem such that fo...
Abstract We study the use of the elaboration preorder (due to ArunKumar and Natarajan) in the framework of up-to techniques for weak bisimulation. We show that elaboration yields a...
When decomposing database schemas, it is desirable that a decomposition is lossless and dependency preserving. A well-known and frequently used result for the relational model stat...
We study convergence properties of empirical minimization of a stochastic strongly convex objective, where the stochastic component is linear. We show that the value attained by t...
-An edge of a graph H with a perfect matching is a fixed edge if it either belongs to none or to all of the perfect matchings of H. It is shown that a connected plane bipartite gra...