Metraipolis › archive › dc_d0cb150e49c2

Scalable Cox Regression via Grouped Risk Sets and Sharper LogSumExp Rates — arXiv:2609.40120

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.40120
License (as archived)
CC0-1.0
Archived
2026-10-07T13:46:54.038Z
SHA-256 of the archived text
78d744f71ec6851ef7a1488d0b38e79c02d0273764c1a63a2f21e04997af2d3a
Stable URL of this page
https://metraipolis.com/documento/dc_d0cb150e49c2

How to cite

Scalable Cox Regression via Grouped Risk Sets and Sharper LogSumExp Rates — arXiv:2609.40120 — arXiv (en), https://arxiv.org/abs/2609.40120 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d0cb150e49c2 (Metraipolis archive dc_d0cb150e49c2, sha256 78d744f71ec6851ef7a1488d0b38e79c02d0273764c1a63a2f21e04997af2d3a)
BibTeX
@misc{dcd0cb150e49c2,
  title = {Scalable Cox Regression via Grouped Risk Sets and Sharper LogSumExp Rates — arXiv:2609.40120},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.40120},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d0cb150e49c2; sha256 78d744f71ec6851ef7a1488d0b38e79c02d0273764c1a63a2f21e04997af2d3a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40120. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Motivated by the computational challenges of large-scale Cox regression, we study stochastic minimization of LogSumExp objectives over large sets. Mini-batch normalizer estimates generally yield biased gradients. We instead use a softplus surrogate that introduces one auxiliary scalar per normalizer and admits unbiased single-sample gradients. For smooth convex LogSumExp objectives, we prove an $O(T^{-1/2})$ averaged objective bound, improving the previous $T^{-1/4}$ analysis. With a strongly convex regularizer on the original variable, we also obtain a last-iterate squared-error rate of $\widetilde{O}(T^{-1})$ without strong convexity in the auxiliary variables. For Cox regression, the normalizers are defined over nested risk sets. We exploit this structure by grouping neighboring failures and sharing one auxiliary variable per group. The resulting compressed objective admits uniform score and curvature bounds that control the errors from grouping and softplus approximation. Together with the general optimization result, these bounds give a mean-square rate of $T^{-4/5}$, up to logarithmic factors, relative to the full Cox solution. The compressed estimator also matches the full estimator's asymptotic distribution. Experiments on synthetic and real survival datasets with slowly decreasing risk sets show a favorable performance relative to stochastic baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.40120 — 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 2026-10-07T13:18:10.508Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).