13 search results - page 3 / 3 » The Importance of Convexity in Learning with Squared Loss |
CORR
2006
Springer
13 years 8 months ago
2006
Springer
The Minimum Description Length principle for online sequence estimation/prediction in a proper learning setup is studied. If the underlying model class is discrete, then the total...
NIPS
2008
13 years 10 months ago
2008
This paper addresses the important tradeoff between privacy and learnability, when designing algorithms for learning from private databases. We focus on privacy-preserving logisti...
CIKM
2009
Springer
14 years 1 months ago
2009
Springer
Traditional ranking mainly focuses on one type of data source, and effective modeling still relies on a sufficiently large number of labeled or supervised examples. However, in m...