569 search results - page 52 / 114 » Online Bounds for Bayesian Algorithms |
COLT
1999
Springer
15 years 2 months ago
1999
Springer
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...
MICAI
2005
Springer
15 years 3 months ago
2005
Springer
Although undirected cycles in directed graphs of Bayesian belief networks have been thoroughly studied, little attention has so far been given to a systematic analysis of directed ...
ICIP
2005
IEEE
15 years 11 months ago
2005
IEEE
A variational Bayesian framework is employed in the paper for image segmentation using color clustering. A Gaussian mixture model is used to represent color distributions. Variati...
ICML
2005
IEEE
15 years 10 months ago
2005
IEEE
We consider online learning where the target concept can change over time. Previous work on expert prediction algorithms has bounded the worst-case performance on any subsequence ...
PKDD
2010
Springer
14 years 8 months ago
2010
Springer
Abstract. Bayesian reinforcement learning (RL) is aimed at making more efficient use of data samples, but typically uses significantly more computation. For discrete Markov Decis...