Based on the coherence principle of de Finetti and a related notion of generalized coherence (g-coherence), we adopt a probabilistic approach to uncertainty based on conditional p...
Veronica Biazzo, Angelo Gilio, Giuseppe Sanfilippo
One of the nice properties of kernel classifiers such as SVMs is that they often produce sparse solutions. However, the decision functions of these classifiers cannot always be u...
—We propose a non-coherent receiver for the fixed detect-and-forward relay channel and derive a closed-form tight upper bound on its bit error probability in Rayleigh fading cha...
We consider the problem of deriving class-size independent generalization bounds for some regularized discriminative multi-category classification methods. In particular, we obtai...
A generalization of deFinetti’s Fundamental Theorem of Probability facilitates coherent assessment, by iterated natural extension, of imprecise probabilities or expectations, co...