We study generalization properties of linear learning algorithms and develop a data dependent approach that is used to derive generalization bounds that depend on the margin distr...
In the problem of learning with positive and unlabeled examples, existing research all assumes that positive examples P and the hidden positive examples in the unlabeled set U are...
We address the problem of designing optimal quantizers for distributed source coding. The generality of our formulation includes both the symmetric and asymmetric scenarios, toget...
We present a new distributed algorithm for creating and maintaining power-efficient topologies in a wireless network. The wireless nodes establish links to neighbouring nodes in a ...
A novel routing algorithm, named Balanced Adaptive Routing Protocol (BARP), is proposed for NoCs to provide adaptive routing and ensure deadlock-free and livelock-free routing at ...
Pejman Lotfi-Kamran, Masoud Daneshtalab, Caro Luca...