Parametric Herding
Abstract
A parametric version of herding is formulated. The nonlinear mapping between consecutive time slices is learned by a form of self-supervised training. The resulting dynamical system generates pseudo-samples that resemble the original data. We show how this parametric herding can be successfully used to compress a dataset consisting of binary digits. It is also verified that high compression rates translate into good prediction performance on unseen test data.
Cite
Text
Chen and Welling. "Parametric Herding." Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010.Markdown
[Chen and Welling. "Parametric Herding." Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010.](https://mlanthology.org/aistats/2010/chen2010aistats-parametric/)BibTeX
@inproceedings{chen2010aistats-parametric,
title = {{Parametric Herding}},
author = {Chen, Yutian and Welling, Max},
booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics},
year = {2010},
pages = {97-104},
volume = {9},
url = {https://mlanthology.org/aistats/2010/chen2010aistats-parametric/}
}