97 search results - page 13 / 20 » Logarithmic Regret Algorithms for Online Convex Optimization |
EMNLP
2009
13 years 5 months ago
2009
The recently introduced online confidence-weighted (CW) learning algorithm for binary classification performs well on many binary NLP tasks. However, for multi-class problems CW l...
COLT
2010
Springer
13 years 5 months ago
2010
Springer
We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known firstor...
NIPS
2007
13 years 9 months ago
2007
We present a novel boosting algorithm, called SoftBoost, designed for sets of binary labeled examples that are not necessarily separable by convex combinations of base hypotheses....
SDM
2008
SIAM
13 years 9 months ago
2008
SIAM
RELIEF is considered one of the most successful algorithms for assessing the quality of features due to its simplicity and effectiveness. It has been recently proved that RELIEF i...
ICML
2009
IEEE
14 years 2 months ago
2009
IEEE
In this work, we extend the ellipsoid method, which was originally designed for convex optimization, for online learning. The key idea is to approximate by an ellipsoid the classi...