8 search results - page 1 / 2 » A primal-dual perspective of online learning algorithms |
ML
2007
ACM
13 years 10 months ago
2007
ACM
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
MCS
2010
Springer
14 years 4 months ago
2010
Springer
Abstract. Oza’s Online Boosting algorithm provides a version of AdaBoost which can be trained in an online way for stationary problems. One perspective is that this enables the p...
WWW
2008
ACM
14 years 11 months ago
2008
ACM
Sponsored search is one of the enabling technologies for today's Web search engines. It corresponds to matching and showing ads related to the user query on the search engine...
SOFSEM
2010
Springer
14 years 7 months ago
2010
Springer
Regret minimization has proven to be a very powerful tool in both computational learning theory and online algorithms. Regret minimization algorithms can guarantee, for a single de...
UAI
1997
14 years 5 days ago
1997
This paper re-examines the problem of parameter estimation in Bayesian networks with missing values and hidden variables from the perspective of recent work in on-line learning [1...