We address the problem of evaluating the risk of a given model accurately at minimal labeling costs. This problem occurs in situations in which risk estimates cannot be obtained f...
Christoph Sawade, Niels Landwehr, Steffen Bickel, ...
In order to obtain better generalization performance in supervised learning, model parameters should be determined appropriately, i.e., they should be determined so that the gener...
We consider multivariate density estimation with identically distributed observations. We study a density estimator which is a convex combination of functions in a dictionary and ...
In this paper, the interpolation mechanism of functional networks is discussed. A kind of fourlayer (with 1 input and 1 output unit) and a five-layer (with double input and single...
This paper extends the game-theoretic notion of internal regret to the case of on-line potfolio selection problems. New sequential investment strategies are designed to minimize th...