Regularized Wasserstein Means for Aligning Distributional Data
Abstract
We propose to align distributional data from the perspective of Wasserstein means. We raise the problem of regularizing Wasserstein means and propose several terms tailored to tackle different problems. Our formulation is based on the variational transportation to distribute a sparse discrete measure into the target domain. The resulting sparse representation well captures the desired property of the domain while reducing the mapping cost. We demonstrate the scalability and robustness of our method with examples in domain adaptation, point set registration, and skeleton layout.
Cite
Text
Mi et al. "Regularized Wasserstein Means for Aligning Distributional Data." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I04.5960Markdown
[Mi et al. "Regularized Wasserstein Means for Aligning Distributional Data." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/mi2020aaai-regularized/) doi:10.1609/AAAI.V34I04.5960BibTeX
@inproceedings{mi2020aaai-regularized,
title = {{Regularized Wasserstein Means for Aligning Distributional Data}},
author = {Mi, Liang and Zhang, Wen and Wang, Yalin},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2020},
pages = {5166-5173},
doi = {10.1609/AAAI.V34I04.5960},
url = {https://mlanthology.org/aaai/2020/mi2020aaai-regularized/}
}