3050 search results - page 208 / 610 » On-line Algorithms in Machine Learning |
128
click to vote
ALT
2009
Springer
15 years 9 months ago
2009
Springer
In this paper the sequential prediction problem with expert advice is considered for the case when the losses of experts suffered at each step can be unbounded. We present some mo...
131
click to vote
ICML
2008
IEEE
16 years 5 months ago
2008
IEEE
Similarity matrices generated from many applications may not be positive semidefinite, and hence can't fit into the kernel machine framework. In this paper, we study the prob...
153
click to vote
NLP
2000
15 years 7 months ago
2000
Abstract. The paper argues that a promising way to improve the success rate of preference-based anaphora resolution algorithms is the use of machine learning. The paper outlines MA...
126
click to vote
ICML
2006
IEEE
16 years 5 months ago
2006
IEEE
We formalize the associative bandit problem framework introduced by Kaelbling as a learning-theory problem. The learning environment is modeled as a k-armed bandit where arm payof...
149
click to vote
ICML
2005
IEEE
16 years 5 months ago
2005
IEEE
We prove a quantitative connection between the expected sum of rewards of a policy and binary classification performance on created subproblems. This connection holds without any ...