Metraipolis › archive › dc_75b4eb9dd92e
The Signed Geometry of One-Shot Recourse: On-Path Validity and the Signed-Curvature Criterion — arXiv:2609.36252
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36252
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:28:54.400Z
- SHA-256 of the archived text
d7024a08cdbaf877807b813d9b137c20c896a1f0351c6e8c2b6b6481ae058a55- Stable URL of this page
https://metraipolis.com/documento/dc_75b4eb9dd92e
How to cite
The Signed Geometry of One-Shot Recourse: On-Path Validity and the Signed-Curvature Criterion — arXiv:2609.36252 — arXiv (en), https://arxiv.org/abs/2609.36252 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75b4eb9dd92e (Metraipolis archive dc_75b4eb9dd92e, sha256 d7024a08cdbaf877807b813d9b137c20c896a1f0351c6e8c2b6b6481ae058a55)
BibTeX
@misc{dc75b4eb9dd92e,
title = {The Signed Geometry of One-Shot Recourse: On-Path Validity and the Signed-Curvature Criterion — arXiv:2609.36252},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36252},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75b4eb9dd92e; sha256 d7024a08cdbaf877807b813d9b137c20c896a1f0351c6e8c2b6b6481ae058a55},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36252. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Closed-form recourse moves a rejected user along the unit gradient $\hat g$ of the classifier score $f$ by the promised distance $d_p=|f(x)|/\|\nabla f(x)\|$, at which the linearized score reaches zero. We ask when this one-shot step succeeds and what additional model queries change. To leading order the step ends on the favorable side exactly when the path curvature $\kappa=\hat g^\top\nabla^2 f(x)\,\hat g$ is nonnegative. Across 80 shallow models, the fraction of rejected users whose step ends there and the fraction with $\kappa\ge0$ correlate at $r=0.985$, although on Fashion-MNIST the first falls below the second by 8.2 points on average. No rule that uses only the score value and gradient can be valid for every score with path curvature bounded by $K$ without overshooting some by order $Kd_p^2/\|\nabla f(x)\|$. When the curvature is also Lipschitz and the step is short, one evaluation of $f$ at the promised point attains the minimax rate among deterministic one-query rules that know the curvature bound and its Lipschitz constant, and split-conformal calibration makes such a rule reach the first crossing or abstain with probability at least $1-\delta$. Training with an asymmetric curvature penalty lets 99-100% of paths cross within the promised step on undershoot-prone shallow data, at about 4-22 times the overshoot of symmetric penalties (Fashion-MNIST, COMPAS). Because $\kappa$ and $d_p$ depend on how the score is scaled, part of this gain can be a longer promised step, and at matched validity a smaller audit of briefly trained models finds no uniform advantage over tuned inflation. Where a per-user line search along the ray is affordable, it is exact to grid resolution and preferable. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.36252 — 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 2026-10-07T16:59:48.134Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).