On the equivalence of weak learnability and linear separability: new relaxations and efficient boosting algorithms
- 4 May 2010
- journal article
- Published by Springer Nature in Machine Learning
- Vol. 80 (2-3) , 141-163
Abstract
No abstract availableKeywords
This publication has 13 references indexed in Scilit:
- Efficient projections onto thel1-ball for learning in high dimensions2008
- Entropy Regularized LPBoost2008
- Analysis of boosting algorithms using the smooth margin functionThe Annals of Statistics, 2007
- A primal-dual perspective of online learning algorithmsMachine Learning, 2007
- Convex Analysis and Nonlinear Optimization2006
- Totally corrective boosting algorithms that maximize the margin2006
- Convex Optimization2004
- Sequential greedy approximation for certain convex optimization problemsIEEE Transactions on Information Theory, 2003
- Game theory, on-line prediction and boosting1996
- Zur Theorie der GesellschaftsspieleMathematische Annalen, 1928