Sciweavers

2900 search results - page 61 / 580
» On the Convergence of Immune Algorithms
Sort
View
JCSS
2006
77views more  JCSS 2006»
14 years 11 months ago
Sequential predictions based on algorithmic complexity
This paper studies sequence prediction based on the monotone Kolmogorov complexity Km=-log m, i.e. based on universal deterministic/one-part MDL. m is extremely close to Solomonof...
Marcus Hutter
COCOON
2009
Springer
15 years 6 months ago
HITS Can Converge Slowly, but Not Too Slowly, in Score and Rank
This paper explores the fundamental question of how many iterations the celebrated HITS algorithm requires on a general graph to converge in score and, perhaps more importantly, in...
Enoch Peserico, Luca Pretto
SDM
2012
SIAM
304views Data Mining» more  SDM 2012»
13 years 2 months ago
Robust Reputation-Based Ranking on Bipartite Rating Networks
With the growth of the Internet and E-commerce, bipartite rating networks are ubiquitous. In such bipartite rating networks, there exist two types of entities: the users and the o...
Rong-Hua Li, Jeffrey Xu Yu, Xin Huang, Hong Cheng
WCE
2007
15 years 1 months ago
An Energy Backpropagation Algorithm
— This paper presents an energy back-propagation algorithm (EBP). Learning and convergence processes of the standard backpropagation algorithm (SBP) are based on the energy funct...
Ahmad Hashim Hussein Aal-Yhia, Ahmad Sharieh
NIPS
2008
15 years 1 months ago
On the Generalization Ability of Online Strongly Convex Programming Algorithms
This paper examines the generalization properties of online convex programming algorithms when the loss function is Lipschitz and strongly convex. Our main result is a sharp bound...
Sham M. Kakade, Ambuj Tewari