Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9:97-104, 2010.
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.