187 search results - page 1 / 38 » Bounding the cost of learned rules |
AI
2000
Springer
13 years 7 months ago
2000
Springer
ALT
2002
Springer
14 years 4 months ago
2002
Springer
Abstract. We consider a problem that is related to the “Universal Encoding Problem” from information theory. The basic goal is to find rules that map “partial information”...
SIGECOM
2010
ACM
14 years 4 days ago
2010
ACM
We explore the striking mathematical connections that exist between market scoring rules, cost function based prediction markets, and no-regret learning. We first show that any c...
COLT
2008
Springer
13 years 9 months ago
2008
Springer
Prediction from expert advice is a fundamental problem in machine learning. A major pillar of the field is the existence of learning algorithms whose average loss approaches that ...
ICML
2004
IEEE
14 years 23 days ago
2004
IEEE
While there is a lot of empirical evidence showing that traditional rule learning approaches work well in practice, it is nearly impossible to derive analytical results about thei...