EUVIMEDTutustu EUVIMEDiin
Crossref

Minimax confidence intervals for the Sliced Wasserstein distance

Tudor Manole, Sivaraman Balakrishnan, Larry Wasserman

Electronic Journal of Statistics · 2022-01-01 · 16 (1) · 2252-2345

DOI: 10.1214/22-ejs2001 ↗

At a glance

Journal article in Electronic Journal of Statistics, published on 2022-01-01. Written by Tudor Manole and 2 co-authors. Cited 21 times so far (Crossref); 85 references.

TiivistelmäBibliografiset tiedotCiteRelated studies

Abstract (original language)

Motivated by the growing popularity of variants of the Wasserstein distance in statistics and machine learning, we study statistical inference for the Sliced Wasserstein distance—an easily computable variant of the Wasserstein distance. Specifically, we construct confidence intervals for the Sliced Wasserstein distance which have finite-sample validity under no assumptions or under mild moment assumptions. These intervals are adaptive in length to the regularity of the underlying distributions. We also bound the minimax risk of estimating the Sliced Wasserstein distance, and as a consequence establish that the lengths of our proposed confidence intervals are minimax optimal over appropriate distribution classes. To motivate the choice of these classes, we also study minimax rates of estimating a distribution under the Sliced Wasserstein distance. These theoretical findings are complemented with a simulation study demonstrating the deficiencies of the classical bootstrap, and the advantages of our proposed methods. We also show strong correspondences between our theoretical predictions and the adaptivity of our confidence interval lengths in simulations. We conclude by demonstrating the use of our confidence intervals in the setting of simulator-based likelihood-free inference. In this setting, contrasting popular approximate Bayesian computation methods, we develop uncertainty quantification methods with rigorous frequentist coverage guarantees.

Cite

APA

Manole, T., Balakrishnan, S., & Wasserman, L. (2022). Minimax confidence intervals for the Sliced Wasserstein distance. Electronic Journal of Statistics, 16(1), 2252-2345. https://doi.org/10.1214/22-ejs2001

Vancouver

Manole T, Balakrishnan S, Wasserman L. Minimax confidence intervals for the Sliced Wasserstein distance. Electronic Journal of Statistics. 2022;16(1):2252-2345. doi:10.1214/22-ejs2001

BibTeX
@article{Manole2022,
  author = {Manole, Tudor and Balakrishnan, Sivaraman and Wasserman, Larry},
  title = {Minimax confidence intervals for the Sliced Wasserstein distance},
  journal = {Electronic Journal of Statistics},
  year = {2022},
  volume = {16},
  number = {1},
  pages = {2252--2345},
  doi = {10.1214/22-ejs2001}
}
Start for free →