Metraipolis › archive › dc_f626dc1d80bc
Score-based Outlier Generation via Controlling the Radon-Nikodym Derivative — arXiv:2609.12113
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12113
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:15:31.040Z
- SHA-256 of the archived text
48e84ac2128903342adcea0a486ae7b2fd9e0714c15a1b77cd8e0dd69aa94f6a- Stable URL of this page
https://metraipolis.com/documento/dc_f626dc1d80bc
How to cite
Score-based Outlier Generation via Controlling the Radon-Nikodym Derivative — arXiv:2609.12113 — arXiv (en), https://arxiv.org/abs/2609.12113 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f626dc1d80bc (Metraipolis archive dc_f626dc1d80bc, sha256 48e84ac2128903342adcea0a486ae7b2fd9e0714c15a1b77cd8e0dd69aa94f6a)
BibTeX
@misc{dcf626dc1d80bc,
title = {Score-based Outlier Generation via Controlling the Radon-Nikodym Derivative — arXiv:2609.12113},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12113},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f626dc1d80bc; sha256 48e84ac2128903342adcea0a486ae7b2fd9e0714c15a1b77cd8e0dd69aa94f6a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12113. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Outliers are important for stress-testing algorithms and understanding system behaviour under rare conditions. Despite being commonly described as low-likelihood events, existing generative approaches rarely control likelihood explicitly. In this work, we introduce a measure-theoretic notion of outliers based on the distribution of log-likelihood values, which is guaranteed to assign higher probability mass to low-likelihood events with a specifiable magnitude. Building on this formulation, we derive how likelihood reweighting modifies the diffusion score and use this relation to motivate a controlled modification of the reverse-time dynamics. In particular, likelihood reweighting implies a scaling of the score function with a control term derived from the Radon-Nikodym derivative of the likelihood distributions. Correspondingly, the updated score function can be obtained with no retraining of the diffusion model. We exploit the Ornstein-Uhlenbeck semigroup underlying diffusion models to motivate an exponentially interpolated controller which approximates the true control. Experiments demonstrate controlled generation of low-likelihood samples while remaining consistent with the data geometry. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Analysis of PDEs (math.AP); Optimization and Control (math.OC); Probability (math.PR); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.12113 — 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 2026-10-16T03:05:44.014Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).