Metraipolis › archive › dc_8cbeeaefa414

The Loss or the Architecture? What Matters in Survival Analysis with Competing Risks — arXiv:2610.23322

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23322
License (as archived)
CC0-1.0
Archived
2026-10-19T09:21:26.198Z
SHA-256 of the archived text
032f3a38a1e4b6494224a6dc9d76635831d994f527ffcfeeab5e1de8d169d91f
Stable URL of this page
https://metraipolis.com/documento/dc_8cbeeaefa414

How to cite

The Loss or the Architecture? What Matters in Survival Analysis with Competing Risks — arXiv:2610.23322 — arXiv (en), https://arxiv.org/abs/2610.23322 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8cbeeaefa414 (Metraipolis archive dc_8cbeeaefa414, sha256 032f3a38a1e4b6494224a6dc9d76635831d994f527ffcfeeab5e1de8d169d91f)
BibTeX
@misc{dc8cbeeaefa414,
  title = {The Loss or the Architecture? What Matters in Survival Analysis with Competing Risks — arXiv:2610.23322},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23322},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8cbeeaefa414; sha256 032f3a38a1e4b6494224a6dc9d76635831d994f527ffcfeeab5e1de8d169d91f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23322. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Often, \emph{eg} in healthcare and predictive maintenance, what matters is which of several competing causes will strike first, and with what probability: survival analysis with competing risks. Corresponding deep learning methods are developed as bundles: a new architecture together with a new training loss, tested on one to five datasets against a handful of baselines. Thus, a state-of-the-art result cannot be attributed to the architecture, the loss, or the evaluation protocol. The coupling is not accidental: with one incidence curve per cause, a network's head is tied to the losses expressible on it. We vary the two axes independently, three losses, two of them strictly proper, on four backbones, across two modalities that tease the axes apart: 20 tabular and 3 pathology-image datasets. One loss wins in both: modelling cumulative incidence directly under censoring weighting. It brings twice as much as benefits a good choice of backbone on competing-risks data, and no more than it on single-event data: the loss is decisive for competing risks. The backbone matters too, and must match the modality: tabular networks lead on tables, pretrained vision encoders on images. The two choices compound rather than substitute. Proper scoring rules reveal these dynamics; the concordance index (C-index), which is not proper, does not separate models: neither axis moves it, not even tuning on the loss built to improve it. This is an avenue of progress: composed, the two give a model nobody has tried, RealMLP or TabM trained with the cumulative-incidence loss, which takes the best Brier score in our benchmark.

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/2610.23322 — 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 2026-10-19T09:17:41.717Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).