Name
Abstract | ||
|---|---|---|
We seek a generalization of regression and principle component analysis (PCA) in a metric space where data points are distributions metrized by the Wasserstein metric. We recast these analyses as multimarginal optimal transport problems. The particular formulation allows efficient computation, ensures existence of optimal solutions, and admits a probabilistic interpretation over the space of paths (line segments). Application of the theory to the interpolation of empirical distributions, images, power spectra, as well as assessing uncertainty in experimental designs, is envisioned. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/LCSYS.2020.3006965 | IEEE Control Systems Letters |
Keywords | DocType | Volume |
Statistical learning,stochastic systems,Wasserstein geometry,measure-valued interpolation,multi-marginal optimal transport | Journal | 5 |
Issue | ISSN | Citations |
3 | 2475-1456 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Karimi Amirhossein | 1 | 0 | 0.34 |
| Ripani Luigia | 2 | 0 | 0.34 |
| Tryphon T. Georgiou | 3 | 211 | 36.71 |