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 ...
Instruction scratchpads have been previously suggested as a way to reduce the worst case execution time (WCET) of hard real-time programs without introducing the analysis issues p...
In the past decade, moving horizon estimation (MHE) has emerged as a powerful technique for estimating the state of a dynamical system in the presence of nonlinearities and disturb...
Angelo Alessandri, Marco Baglietto, Giorgio Battis...
Abstract. An important unsolved problem in structural bioinformatics is that of protein structure prediction (PSP), the reconstruction of a biologically plausible three-dimensional...
Stefano Teso, Cristina Di Risio, Andrea Passerini,...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...