Making transport more robust and interpretable by moving data through a small number of anchor points

Chi-Heng Lin, Mehdi Azabou, Eva Dyer
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:6631-6641, 2021.

Abstract

Optimal transport (OT) is a widely used technique for distribution alignment, with applications throughout the machine learning, graphics, and vision communities. Without any additional structural assumptions on transport, however, OT can be fragile to outliers or noise, especially in high dimensions. Here, we introduce Latent Optimal Transport (LOT), a new approach for OT that simultaneously learns low-dimensional structure in data while leveraging this structure to solve the alignment task. The idea behind our approach is to learn two sets of “anchors” that constrain the flow of transport between a source and target distribution. In both theoretical and empirical studies, we show that LOT regularizes the rank of transport and makes it more robust to outliers and the sampling density. We show that by allowing the source and target to have different anchors, and using LOT to align the latent spaces between anchors, the resulting transport plan has better structural interpretability and highlights connections between both the individual data points and the local geometry of the datasets.

Cite this Paper


BibTeX
@InProceedings{pmlr-v139-lin21a, title = {Making transport more robust and interpretable by moving data through a small number of anchor points}, author = {Lin, Chi-Heng and Azabou, Mehdi and Dyer, Eva}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {6631--6641}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/lin21a/lin21a.pdf}, url = {https://proceedings.mlr.press/v139/lin21a.html}, abstract = {Optimal transport (OT) is a widely used technique for distribution alignment, with applications throughout the machine learning, graphics, and vision communities. Without any additional structural assumptions on transport, however, OT can be fragile to outliers or noise, especially in high dimensions. Here, we introduce Latent Optimal Transport (LOT), a new approach for OT that simultaneously learns low-dimensional structure in data while leveraging this structure to solve the alignment task. The idea behind our approach is to learn two sets of “anchors” that constrain the flow of transport between a source and target distribution. In both theoretical and empirical studies, we show that LOT regularizes the rank of transport and makes it more robust to outliers and the sampling density. We show that by allowing the source and target to have different anchors, and using LOT to align the latent spaces between anchors, the resulting transport plan has better structural interpretability and highlights connections between both the individual data points and the local geometry of the datasets.} }
Endnote
%0 Conference Paper %T Making transport more robust and interpretable by moving data through a small number of anchor points %A Chi-Heng Lin %A Mehdi Azabou %A Eva Dyer %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-lin21a %I PMLR %P 6631--6641 %U https://proceedings.mlr.press/v139/lin21a.html %V 139 %X Optimal transport (OT) is a widely used technique for distribution alignment, with applications throughout the machine learning, graphics, and vision communities. Without any additional structural assumptions on transport, however, OT can be fragile to outliers or noise, especially in high dimensions. Here, we introduce Latent Optimal Transport (LOT), a new approach for OT that simultaneously learns low-dimensional structure in data while leveraging this structure to solve the alignment task. The idea behind our approach is to learn two sets of “anchors” that constrain the flow of transport between a source and target distribution. In both theoretical and empirical studies, we show that LOT regularizes the rank of transport and makes it more robust to outliers and the sampling density. We show that by allowing the source and target to have different anchors, and using LOT to align the latent spaces between anchors, the resulting transport plan has better structural interpretability and highlights connections between both the individual data points and the local geometry of the datasets.
APA
Lin, C., Azabou, M. & Dyer, E.. (2021). Making transport more robust and interpretable by moving data through a small number of anchor points. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:6631-6641 Available from https://proceedings.mlr.press/v139/lin21a.html.

Related Material