We propose a method to train a cascade of classifiers by simultaneously optimizing all its stages. The approach relies on the idea of optimizing soft cascades. In particular, inst...
Abstract. Markov logic, as a highly expressive representation formalism that essentially combines the semantics of probabilistic graphical models with the full power of first-orde...
Dominik Jain, Bernhard Kirchlechner, Michael Beetz
Although theoretical results for several algorithms in many application domains were presented during the last decades, not all algorithms can be analyzed fully theoretically. Exp...
This paper is concerned with classifying high dimensional data into one of two categories. In various settings, such as when dealing with fMRI and microarray data, the number of v...
We develop a new tool for data-dependent analysis of the exploration-exploitation trade-off in learning under limited feedback. Our tool is based on two main ingredients. The fi...