Metraipolis › archive › dc_ac93c899a472

Robust-by-Design Distributional Learning from Contaminated Samples — arXiv:2610.40884

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40884
License (as archived)
CC0-1.0
Archived
2026-11-03T08:12:47.442Z
SHA-256 of the archived text
d922a4b100a5c206714eb35ccf0815df7cc9c920744047b8e8f12da9859dd609
Stable URL of this page
https://metraipolis.com/documento/dc_ac93c899a472

How to cite

Robust-by-Design Distributional Learning from Contaminated Samples — arXiv:2610.40884 — arXiv (en), https://arxiv.org/abs/2610.40884 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac93c899a472 (Metraipolis archive dc_ac93c899a472, sha256 d922a4b100a5c206714eb35ccf0815df7cc9c920744047b8e8f12da9859dd609)
BibTeX
@misc{dcac93c899a472,
  title = {Robust-by-Design Distributional Learning from Contaminated Samples — arXiv:2610.40884},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40884},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac93c899a472; sha256 d922a4b100a5c206714eb35ccf0815df7cc9c920744047b8e8f12da9859dd609},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40884. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern data analysis pipelines increasingly rely on large datasets assembled through retrieval, scraping, automated filtering, and post-hoc curation, where the observed sample is often a contaminated mixture rather than the target population. Standard distributional objectives either ignore contamination and converge to the wrong target, or retain only a small trusted subset and discard most of the data. We study supervised and unsupervised learning when a clean reference sample is compared with a pooled sample from $r=(1-\epsilon)q+\epsilon z$, where $q$ is the latent target distribution and $z$ is an unknown contaminant. Motivated by settings with noisy membership scores for all observations and exact labels for a small audited subset, we propose contamination-corrected maximum mean discrepancy (CC-MMD), a design-based estimator that combines proxy scores with audited residual corrections to recover the oracle MMD that would have been computed from the latent clean sample. CC-MMD requires no calibration assumption on the proxy scores and no structural assumptions on the contaminant beyond standard kernel regularity. We prove finite-population design-unbiasedness of the corrected kernel sums, establish asymptotic normality of the audit correction, and show consistency for the target discrepancy $\mathrm{MMD}^2(p,q;k)$. Empirically, CC-MMD tracks the oracle under increasing contamination, improves parameter recovery and prediction in contaminated regression, and enables generative models trained on heavily corrupted mixtures to recover the clean target distribution. These results show that contaminated data need not be discarded or treated as the estimand. With sparse trusted labels and abundant noisy supervision, distributional objectives can be made robust by design.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.40884 — 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 2026-11-03T08:02:38.969Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).