Sciweavers

4047 search results - page 191 / 810
» Some Properties and Some Problems on Set Functors
Sort
View
COLT
1999
Springer
15 years 10 months ago
Regret Bounds for Prediction Problems
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...
Geoffrey J. Gordon
SIAMDM
2010
113views more  SIAMDM 2010»
15 years 1 months ago
The VPN Problem with Concave Costs
We consider the following network design problem. We are given an undirected network with costs on the edges, a set of terminals, and an upper bound for each terminal limiting the ...
Samuel Fiorini, Gianpaolo Oriolo, Laura Sanit&agra...
EMO
2003
Springer
86views Optimization» more  EMO 2003»
15 years 11 months ago
No Free Lunch and Free Leftovers Theorems for Multiobjective Optimisation Problems
Abstract. The classic NFL theorems are invariably cast in terms of single objective optimization problems. We confirm that the classic NFL theorem holds for general multiobjective ...
David Corne, Joshua D. Knowles
GECCO
2008
Springer
143views Optimization» more  GECCO 2008»
15 years 7 months ago
Application domain study of evolutionary algorithms in optimization problems
This paper deals with the problem of comparing and testing evolutionary algorithms, that is, the benchmarking problem, from an analysis point of view. A practical study of the app...
Pilar Caamaño, Francisco Bellas, José...
COR
2007
106views more  COR 2007»
15 years 6 months ago
On a stochastic sequencing and scheduling problem
We present a framework for solving multistage pure 0–1 programs for a widely used sequencing and scheduling problem with uncertainty in the objective function coefficients, the...
Antonio Alonso-Ayuso, Laureano F. Escudero, M. Ter...