Sciweavers

3049 search results - page 325 / 610
» On the Convergence of Bound Optimization Algorithms
Sort
View
JAIR
2002
163views more  JAIR 2002»
15 years 6 months ago
Efficient Reinforcement Learning Using Recursive Least-Squares Methods
The recursive least-squares (RLS) algorithm is one of the most well-known algorithms used in adaptive filtering, system identification and adaptive control. Its popularity is main...
Xin Xu, Hangen He, Dewen Hu
CDC
2008
IEEE
109views Control Systems» more  CDC 2008»
16 years 1 months ago
Average consensus over small world networks: A probabilistic framework
— It has been observed that adding a few long range edges to certain graph topologies can significantly increase the rate of convergence for consensus algorithms. A notable exam...
Pedram Hovareshti, John S. Baras, Vijay Gupta
CCS
2005
ACM
16 years 6 days ago
Deciding security of protocols against off-line guessing attacks
We provide an effective procedure for deciding the existence of off-line guessing attacks on security protocols, for a bounded number of sessions. The procedure consists of a co...
Mathieu Baudet
AUTOMATICA
2006
111views more  AUTOMATICA 2006»
15 years 6 months ago
The minimal disturbance invariant set: Outer approximations via its partial sums
This paper is concerned with outer approximations of the minimal disturbance invariant set (MDIS) of a discrete-time linear system with an additive set-bounded disturbance. The k-...
Chong Jin Ong, Elmer G. Gilbert
ICPR
2010
IEEE
15 years 5 months ago
Incremental Training of Multiclass Support Vector Machines
We present a new method for the incremental training of multiclass Support Vector Machines that provides computational efficiency for training problems in the case where the trai...
Symeon Nikitidis, Nikos Nikolaidis, Ioannis Pitas