Sciweavers

5109 search results - page 30 / 1022
» On Learning Limiting Programs
Sort
View
CDC
2009
IEEE
151views Control Systems» more  CDC 2009»
14 years 2 months ago
Shortest path optimization under limited information
— The problem of finding an optimal path in an uncertain graph arises in numerous applications, including network routing, path-planning for vehicles, and the control of finite...
Michael Rinehart, Munther A. Dahleh
IJAC
2008
58views more  IJAC 2008»
13 years 10 months ago
Limit Preservation Properties of the Greatest Semilattice Image Functor
We study what kinds of limits are preserved by the greatest semilattice image functor from the category of all semigroups to its subcategory of all semilattices. The second autho...
George Janelidze, Valdis Laan, László...
MP
2007
89views more  MP 2007»
13 years 9 months ago
Globally convergent limited memory bundle method for large-scale nonsmooth optimization
Many practical optimization problems involve nonsmooth (that is, not necessarily differentiable) functions of thousands of variables. In the paper [Haarala, Miettinen, M¨akel¨a,...
Napsu Haarala, Kaisa Miettinen, Marko M. Mäke...
ICML
2005
IEEE
14 years 10 months ago
Harmonic mixtures: combining mixture models and graph-based methods for inductive and scalable semi-supervised learning
Graph-based methods for semi-supervised learning have recently been shown to be promising for combining labeled and unlabeled data in classification problems. However, inference f...
Xiaojin Zhu, John D. Lafferty
ESANN
2006
13 years 11 months ago
Reducing policy degradation in neuro-dynamic programming
We focus on neuro-dynamic programming methods to learn state-action value functions and outline some of the inherent problems to be faced, when performing reinforcement learning in...
Thomas Gabel, Martin Riedmiller