3694 search results - page 159 / 739 » Stochastic complexity in learning |
NIPS
2004
14 years 11 months ago
2004
In this paper we propose a novel method for learning a Mahalanobis distance measure to be used in the KNN classification algorithm. The algorithm directly maximizes a stochastic v...
IJCAI
2003
14 years 11 months ago
2003
We investigate the problem of non-covariant behavior of policy gradient reinforcement learning algorithms. The policy gradient approach is amenable to analysis by information geom...
PRL
2000
14 years 9 months ago
2000
The need to
ICML
2007
IEEE
15 years 11 months ago
2007
IEEE
We describe and analyze a simple and effective iterative algorithm for solving the optimization problem cast by Support Vector Machines (SVM). Our method alternates between stocha...
COLT
2008
Springer
14 years 12 months ago
2008
Springer
In the multi-armed bandit (MAB) problem there are k distributions associated with the rewards of playing each of k strategies (slot machine arms). The reward distributions are ini...