Non-Linear Metric Learning
Abstract
In this paper, we introduce two novel metric learning algorithms, χ2-LMNN and GB-LMNN, which are explicitly designed to be non-linear and easy-to-use. The two approaches achieve this goal in fundamentally different ways: χ2-LMNN inherits the computational benefits of a linear mapping from linear metric learning, but uses a non-linear χ2-distance to explicitly capture similarities within histogram data sets; GB-LMNN applies gradient-boosting to learn non-linear mappings directly in function space and takes advantage of this approach's robustness, speed, parallelizability and insensitivity towards the single additional hyper-parameter. On various benchmark data sets, we demonstrate these methods not only match the current state-of-the-art in terms of kNN classification error, but in the case of χ2-LMNN, obtain best results in 19 out of 20 learning settings.
Cite
Text
Kedem et al. "Non-Linear Metric Learning." Neural Information Processing Systems, 2012.Markdown
[Kedem et al. "Non-Linear Metric Learning." Neural Information Processing Systems, 2012.](https://mlanthology.org/neurips/2012/kedem2012neurips-nonlinear/)BibTeX
@inproceedings{kedem2012neurips-nonlinear,
title = {{Non-Linear Metric Learning}},
author = {Kedem, Dor and Tyree, Stephen and Sha, Fei and Lanckriet, Gert R. and Weinberger, Kilian Q.},
booktitle = {Neural Information Processing Systems},
year = {2012},
pages = {2573-2581},
url = {https://mlanthology.org/neurips/2012/kedem2012neurips-nonlinear/}
}