Sciweavers

291 search results - page 22 / 59
» The Convergence of Contrastive Divergences
Sort
View
WSC
2004
15 years 7 months ago
On-Demand Computation of Policy Based Routes for Large-Scale Network Simulation
Routing table storage demands pose a significant obstacle for large-scale network simulation. On-demand computation of routes can alleviate those problems for models that do not r...
Michael Liljenstam, David M. Nicol
PKDD
2010
Springer
169views Data Mining» more  PKDD 2010»
15 years 4 months ago
Efficient and Numerically Stable Sparse Learning
We consider the problem of numerical stability and model density growth when training a sparse linear model from massive data. We focus on scalable algorithms that optimize certain...
Sihong Xie, Wei Fan, Olivier Verscheure, Jiangtao ...
SIAMMAX
2010
113views more  SIAMMAX 2010»
15 years 24 days ago
Approximate Nullspace Iterations for KKT Systems
The aim of the paper is to provide a theoretical basis for approximate reduced SQP methods. In contrast to inexact reduced SQP methods, the forward and the adjoint problem accuraci...
Kazufumi Ito, Karl Kunisch, Volker Schulz, Ilia Gh...
SIAMSC
2008
165views more  SIAMSC 2008»
15 years 6 months ago
Iterated Hard Shrinkage for Minimization Problems with Sparsity Constraints
Abstract. A new iterative algorithm for the solution of minimization problems in infinitedimensional Hilbert spaces which involve sparsity constraints in form of p-penalties is pro...
Kristian Bredies, Dirk A. Lorenz
ICML
2001
IEEE
16 years 6 months ago
Off-Policy Temporal Difference Learning with Function Approximation
We introduce the first algorithm for off-policy temporal-difference learning that is stable with linear function approximation. Off-policy learning is of interest because it forms...
Doina Precup, Richard S. Sutton, Sanjoy Dasgupta