Metraipolis › archive › dc_8b26431b970d
ELIPPS: Exact Learning for Inverse Problems from Partial Self-supervision — arXiv:2609.23683
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23683
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T21:42:41.591Z
- SHA-256 of the archived text
e54f5884500b1d93db288b5c60c030cb7aabdff775826d5f04bdd71f40ffe4a4- Stable URL of this page
https://metraipolis.com/documento/dc_8b26431b970d
How to cite
ELIPPS: Exact Learning for Inverse Problems from Partial Self-supervision — arXiv:2609.23683 — arXiv (en), https://arxiv.org/abs/2609.23683 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b26431b970d (Metraipolis archive dc_8b26431b970d, sha256 e54f5884500b1d93db288b5c60c030cb7aabdff775826d5f04bdd71f40ffe4a4)
BibTeX
@misc{dc8b26431b970d,
title = {ELIPPS: Exact Learning for Inverse Problems from Partial Self-supervision — arXiv:2609.23683},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23683},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b26431b970d; sha256 e54f5884500b1d93db288b5c60c030cb7aabdff775826d5f04bdd71f40ffe4a4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23683. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In undersampled inverse problems (such as sparse-view computed tomography), only a small number of measurements are collected, which reduces radiation exposure and acquisition time and cost, and can also address the inaccessibility of certain acquisition arrangements. Most learning-based methods for such problems require supervision in the form of fully sampled measurements and ground-truth images, which are costly or even infeasible to acquire. To overcome this issue, we propose \emph{Exact Learning for Inverse Problems from Partial Self-supervision} (ELIPPS), an incomplete self-supervised training paradigm for undersampled inverse problems that requires neither ground-truth images nor fully sampled measurements. ELIPPS learns solely from incomplete forward measurements on a fixed incomplete supervision set. Our theory shows that when the data distribution is invariant under certain transformations, minimizing a masked empirical risk is equivalent to minimizing the full self-supervised risk, i.e. the risk against the complete, noise-free measurement. The equivalence is exact for arbitrary equivariant hypothesis classes and holds for signal-dependent noise such as the pre-log Poisson statistics of low-dose tomography, and for the log-transformed count model up to a quantifiable bias. When the underlying coverage condition is only approximately satisfied on a discrete grid, we give a stability estimate in terms of the associated frame constants and the irreducible error of the inverse problem. We realize ELIPPS for computed tomography by exploiting rotation and reflection invariance. In our experiments, ELIPPS substantially outperforms naive masked supervision and reaches the same order of accuracy as a reference model trained with full clean measurements.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-22 in math.NA).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2609.23683 — 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 2026-10-09T21:22:11.584Z dalla pagina https://arxiv.org/catchup/math.NA/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).