11 search results - page 1 / 3 » Sample compression bounds for decision trees |
ICML
2007
IEEE
14 years 12 months ago
2007
IEEE
We propose a formulation of the Decision Tree learning algorithm in the Compression settings and derive tight generalization error bounds. In particular, we propose Sample Compres...
FOCS
2008
IEEE
14 years 5 months ago
2008
IEEE
We show a tight lower bound of Ω(N log log N) on the number of transmissions required to compute several functions (including the parity function and the majority function) in a...
ICML
1998
IEEE
14 years 12 months ago
1998
IEEE
In this work, we present a new bottom-up algorithmfor decision tree pruning that is very e cient requiring only a single pass through the given tree, and prove a strong performanc...
KDD
2003
ACM
14 years 11 months ago
2003
ACM
Decision tree construction is a well studied problem in data mining. Recently, there has been much interest in mining streaming data. Domingos and Hulten have presented a one-pass...
COLT
2008
Springer
14 years 29 days ago
2008
Springer
We describe and explore a new perspective on the sample complexity of active learning. In many situations where it was generally believed that active learning does not help, we sh...