Metraipolis › archive › dc_ce854cb60176
Scalable Bayesian Gaussian Process Classification for Cancer Histopathology: Calibrated Uncertainty Under Distribution Shift — arXiv:2611.07127
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07127
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:44:05.575Z
- SHA-256 of the archived text
9f6e3def3ae1184eb52a4174e60e8d25e501cbffea24041afec7d1b480847206- Stable URL of this page
https://metraipolis.com/documento/dc_ce854cb60176
How to cite
Scalable Bayesian Gaussian Process Classification for Cancer Histopathology: Calibrated Uncertainty Under Distribution Shift — arXiv:2611.07127 — arXiv (en), https://arxiv.org/abs/2611.07127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce854cb60176 (Metraipolis archive dc_ce854cb60176, sha256 9f6e3def3ae1184eb52a4174e60e8d25e501cbffea24041afec7d1b480847206)
BibTeX
@misc{dcce854cb60176,
title = {Scalable Bayesian Gaussian Process Classification for Cancer Histopathology: Calibrated Uncertainty Under Distribution Shift — arXiv:2611.07127},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07127},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce854cb60176; sha256 9f6e3def3ae1184eb52a4174e60e8d25e501cbffea24041afec7d1b480847206},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable uncertainty quantification is essential for clinical deployment of cancer diagnosis models, yet neural networks and variational Gaussian process methods can produce overconfident predictions, particularly under the distribution shifts that arise when models trained at one hospital are applied at another. We present a scalable Bayesian Gaussian Process Classification (GPC) framework that operates on frozen pathology foundation model embeddings (Phikon) and combines accelerated Randomly Pivoted Cholesky (RPCholesky) for low-rank kernel factorization, Hamiltonian Monte Carlo (HMC) with non-centered parameterization for posterior sampling, and a pivots-as-inducing-points scheme for prediction. This makes HMC posterior sampling in the low-rank latent representation tractable at N approximately 300,000 training points, enabling HC-based low-rank GPC on substantially larger datasets than prior MCMC-based demonstrations. We evaluate on two histopathology benchmarks for breast cancer metastasis detection: PCam and CAMELYON17-WILDS, where the latter tests calibration under hospital-level distribution shift. Compared to stochastic variational GP and neural network baselines, our method improves calibration and predictive performance - reducing expected calibration error by up to 88% and false negative rate by up to 90% - with the largest gains appearing under distribution shift, suggesting that HMC-based posterior sampling provides more trustworthy uncertainty estimates for cross-site pathology classification. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.07127 — 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 2026-11-06T14:21:42.613Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).