Metraipolis › archive › dc_759ebfd3377a
Adaptive Computation with Conformal Certification — arXiv:2610.19189
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19189
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:15:16.018Z
- SHA-256 of the archived text
b30f7c073da6849338df116116edd0aa24a719051833f7ac04c3b7888e660e5d- Stable URL of this page
https://metraipolis.com/documento/dc_759ebfd3377a
How to cite
Adaptive Computation with Conformal Certification — arXiv:2610.19189 — arXiv (en), https://arxiv.org/abs/2610.19189 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_759ebfd3377a (Metraipolis archive dc_759ebfd3377a, sha256 b30f7c073da6849338df116116edd0aa24a719051833f7ac04c3b7888e660e5d)
BibTeX
@misc{dc759ebfd3377a,
title = {Adaptive Computation with Conformal Certification — arXiv:2610.19189},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19189},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_759ebfd3377a; sha256 b30f7c073da6849338df116116edd0aa24a719051833f7ac04c3b7888e660e5d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19189. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scientific imaging data involving medical (e.g., 3D radiographic, microscopic images) and astronomical sensors pose different challenges from natural images. One key challenge is that these datasets are often orders of magnitude larger than natural images. Efficient training and inference on such data is challenging due to the increased hardware requirements, often needing bespoke solutions. Moreover, the relevant objects such as tumors and astronomical phenomena are sparsely distributed with respect to the background information. Standard efficiency techniques like quantization and pruning apply uniform scaling of all regions, potentially compromising the precision/fidelity of predictions. Thus, efficient methods that reduce computational requirements without losing resolution for relevant parts of the data and with uncertainty estimates on predictions are essential. We present \textit{Conformal Adaptation} with risk guarantees for uncertainty-aware sparse computations. Our formalism is general, spanning dense pixel-level classification and regression tasks where hierarchical models predict at low resolution, certify the signal using conformal risk control, and refine the certified predictions. We benchmark our method on multiple tasks such as 3D medical image segmentation, 2D galaxy flux prediction, and 1D calcium spike rate prediction, achieving $2.5$--$72\times$ wall-clock speedup across the various tasks, including on commodity CPUs.
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/2610.19189 — 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 2026-10-15T13:53:35.541Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).