Abstract. We develop three new techniques to build on the recent advances in online learning with kernels. First, we show that an exponential speed-up in prediction time per trial ...
Dierence Bound Matrices (DBMs) are the most commonly used data structure for model checking timed automata. Since long they are being used in successful tools like Kronos or UPPAA...
This paper considers algorithms and complexity results for the generation of counterexamples in model checking of probabilistic until-formulae in discrete-time Markov chains (DTMCs...
We present a simple new Monte Carlo algorithm for evaluating probabilities of observations in complex latent variable models, such as Deep Belief Networks. While the method is bas...
The Minimum Description Length principle for online sequence estimation/prediction in a proper learning setup is studied. If the underlying model class is discrete, then the total...