Predicting knowledge in an ontology stream
Freddy Lécué, Jeff Z. Pan
IJCAI 2013
Recently, sample complexity bounds have been derived for problems involving linear functions such as neural networks and support vector machines. In many of these theoretical studies, the concept of covering numbers played an important role. It is thus useful to study covering numbers for linear function classes. In this paper, we investigate two closely related methods to derive upper bounds on these covering numbers. The first method, already employed in some earlier studies, relies on the so-called Maurey's lemma; the second method uses techniques from the mistake bound framework in online learning. We compare results from these two methods, as well as their consequences in some learning formulations.
Freddy Lécué, Jeff Z. Pan
IJCAI 2013
Mustansar Fiaz, Mubashir Noman, et al.
IGARSS 2025
Rie Kubota Ando
CoNLL 2006
Susumu Horiguchi, Takeo Nakada
Journal of Parallel and Distributed Computing