590 search results - page 71 / 118 » Can We Learn to Beat the Best Stock |
AAAI
2012
13 years 5 days ago
2012
Kernel methods have been successfully applied to many machine learning problems. Nevertheless, since the performance of kernel methods depends heavily on the type of kernels being...
CORR
2000
Springer
14 years 9 months ago
2000
Springer
In real-world environments it usually is difficult to specify target operating conditions precisely, for example, target misclassification costs. This uncertainty makes building ro...
ICML
1997
IEEE
15 years 10 months ago
1997
IEEE
Abstract: We investigate the structure of model selection problems via the bias/variance decomposition. In particular, we characterize the essential structure of a model selection ...
COLT
2010
Springer
14 years 7 months ago
2010
Springer
We consider the problem of planning in a stochastic and discounted environment with a limited numerical budget. More precisely, we investigate strategies exploring the set of poss...
CORR
2010
Springer
14 years 10 months ago
2010
Springer
We consider the classical multi-armed bandit problem with Markovian rewards. When played an arm changes its state in a Markovian fashion while it remains frozen when not played. Th...