Metraipolis › archive › dc_3ed3cfac0ed8

Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning — arXiv:2608.13418

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13418
License (as archived)
CC0-1.0
Archived
2026-10-19T04:27:56.302Z
SHA-256 of the archived text
eb8fa9351d55dc61fcf1559c16d8e0fa2e3a8e4274299a9165ac777c091a7e38
Stable URL of this page
https://metraipolis.com/documento/dc_3ed3cfac0ed8

How to cite

Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning — arXiv:2608.13418 — arXiv (en), https://arxiv.org/abs/2608.13418 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ed3cfac0ed8 (Metraipolis archive dc_3ed3cfac0ed8, sha256 eb8fa9351d55dc61fcf1559c16d8e0fa2e3a8e4274299a9165ac777c091a7e38)
BibTeX
@misc{dc3ed3cfac0ed8,
  title = {Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning — arXiv:2608.13418},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13418},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ed3cfac0ed8; sha256 eb8fa9351d55dc61fcf1559c16d8e0fa2e3a8e4274299a9165ac777c091a7e38},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13418. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Given a dataset where a portion of the samples are contaminated, our goal is to recover the underlying clean population distribution. To this end, we propose Wasserstein Filtering (WF), a novel sample selection framework that discards a fraction of suspicious samples and estimates the target distribution using the empirical measure of the remaining data. The core insight is to select a subset of samples whose empirical distribution maximizes its Wasserstein distance to the fully contaminated empirical distribution, thereby preferentially isolating and removing geometrically influential outliers. To render this optimization computationally tractable, we introduce three algorithms: a marginal screening scheme, SinkMarg, and two joint optimization algorithms, SinkWF and SlicedWF, leveraging entropic optimal transport and sliced Wasserstein approximations, respectively. On the theoretical front, we introduce the Far Exclusion and Local Projection (FELP) contamination model, which characterizes corruptions consisting of well-separated outliers and locally indistinguishable perturbations. Under this model, we prove that the WF estimator achieves minimax optimality over distribution families with bounded covariance. Extensive numerical experiments on synthetic datasets, benchmark anomaly detection suites, and robust generative learning with diffusion models demonstrate that WF serves as a highly practical, model-agnostic preprocessing tool. It delivers competitive outlier detection performance and provides substantial downstream benefits for generative modeling under heavy contamination.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.13418 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:20:35.914Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).