Metraipolis › archive › dc_7499bcfe8157

Distributionally Robust Survival Models under Subpopulation Shift and Outlier Contamination — arXiv:2610.02868

Source: arXiv
Original: https://arxiv.org/abs/2610.02868
License (as archived): CC0-1.0
Archived: 2026-10-05T22:50:17.822Z
SHA-256 of the archived text: fbdc64811684f688d8540dc5a4ba0b0aa86246d5731f44b3dbdd24203b150dcc
Stable URL of this page: https://metraipolis.com/documento/dc_7499bcfe8157

How to cite

Distributionally Robust Survival Models under Subpopulation Shift and Outlier Contamination — arXiv:2610.02868 — arXiv, https://arxiv.org/abs/2610.02868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7499bcfe8157 (Metraipolis archive dc_7499bcfe8157, sha256 fbdc64811684f688d8540dc5a4ba0b0aa86246d5731f44b3dbdd24203b150dcc)

BibTeX

@misc{dc7499bcfe8157,
  title = {Distributionally Robust Survival Models under Subpopulation Shift and Outlier Contamination — arXiv:2610.02868},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02868},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7499bcfe8157; sha256 fbdc64811684f688d8540dc5a4ba0b0aa86246d5731f44b3dbdd24203b150dcc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning robust survival models under distribution shift is an important but challenging problem in many applications. In heterogeneous populations, a model that performs well on average may still perform poorly on certain subpopulations, and this issue becomes even more severe when the training data are contaminated by outliers. In this paper, we propose a novel distributionally robust framework for survival analysis that jointly addresses latent subpopulation shift and outlier contamination. The proposed method combines an outer minimization that selects a refined nominal distribution by reducing the influence of contaminated samples and an inner maximization that focuses on the most challenging subpopulation. This formulation directly accommodates non-decomposable survival losses while preserving interactions across samples, including the risk-set structure of the Cox negative partial log-likelihood. We develop an alternating gradient-based algorithm with outer updates derived from the KKT conditions of the inner maximization. Experiments on simulated data and two survival benchmarks demonstrate that the proposed method remains robust when subpopulation shift and outlier contamination occur simultaneously. It stabilizes training in contaminated settings and substantially improves worst-group performance across both linear and nonlinear survival models, while maintaining competitive and sometimes superior overall performance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02868 — 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 2026-10-05T22:45:55.802Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).