Learning transformations for classification forests
Publication
, Conference
Qiu, Q; Sapiro, G
Published in: 2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings
January 1, 2014
This work introduces a transformation-based learner model for classification forests. The weak learner at each split node plays a crucial role in a classification tree. We propose to optimize the splitting objective by learning a linear transformation on subspaces using nuclear norm as the optimization criteria. The learned linear transformation restores a low-rank structure for data from the same class, and, at the same time, maximizes the separation between different classes, thereby improving the performance of the split function. Theoretical and experimental results support the proposed framework.
Duke Scholars
Published In
2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings
Publication Date
January 1, 2014
Citation
APA
Chicago
ICMJE
MLA
NLM
Qiu, Q., & Sapiro, G. (2014). Learning transformations for classification forests. In 2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings.
Qiu, Q., and G. Sapiro. “Learning transformations for classification forests.” In 2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings, 2014.
Qiu Q, Sapiro G. Learning transformations for classification forests. In: 2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings. 2014.
Qiu, Q., and G. Sapiro. “Learning transformations for classification forests.” 2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings, 2014.
Qiu Q, Sapiro G. Learning transformations for classification forests. 2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings. 2014.
Published In
2nd International Conference on Learning Representations, ICLR 2014 - Conference Track Proceedings
Publication Date
January 1, 2014