3050 search results - page 178 / 610 » On-line Algorithms in Machine Learning |
128
click to vote
ICML
2003
IEEE
16 years 4 months ago
2003
IEEE
We present a learning framework for Markovian decision processes that is based on optimization in the policy space. Instead of using relatively slow gradient-based optimization al...
140
click to vote
ICML
2002
IEEE
16 years 4 months ago
2002
IEEE
We study generalization properties of linear learning algorithms and develop a data dependent approach that is used to derive generalization bounds that depend on the margin distr...
106
click to vote
ALT
2010
Springer
15 years 5 months ago
2010
Springer
We further develop the idea that the PAC-Bayes prior can be informed by the data-generating distribution. We prove sharp bounds for an existing framework of Gibbs algorithms, and ...
139
click to vote
COLT
1999
Springer
15 years 8 months ago
1999
Springer
We focus on methods to solve multiclass learning problems by using only simple and efficient binary learners. We investigate the approach of Dietterich and Bakiri [2] based on er...
148
click to vote
ML
2010
ACM
14 years 10 months ago
2010
ACM
Graph representations of data are increasingly common. Such representations arise in a variety of applications, including computational biology, social network analysis, web applic...