Metraipolis › archive › dc_796eb3a075a7

Multi-Dataset Inverse Problem Solving with Distributed Generative AI — arXiv:2608.26283

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26283
License (as archived)
CC0-1.0
Archived
2026-10-17T15:28:22.229Z
SHA-256 of the archived text
a0c0fd5ec2177f3b39b19411142d11707cbc71b897f18a846256433aa78e0687
Stable URL of this page
https://metraipolis.com/documento/dc_796eb3a075a7

How to cite

Multi-Dataset Inverse Problem Solving with Distributed Generative AI — arXiv:2608.26283 — arXiv (en), https://arxiv.org/abs/2608.26283 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_796eb3a075a7 (Metraipolis archive dc_796eb3a075a7, sha256 a0c0fd5ec2177f3b39b19411142d11707cbc71b897f18a846256433aa78e0687)
BibTeX
@misc{dc796eb3a075a7,
  title = {Multi-Dataset Inverse Problem Solving with Distributed Generative AI — arXiv:2608.26283},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26283},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_796eb3a075a7; sha256 a0c0fd5ec2177f3b39b19411142d11707cbc71b897f18a846256433aa78e0687},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26283. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Extracting a shared set of unknown, not directly measurable quantities from multiple, heterogeneous datasets is a common challenge across scientific domains. A prominent example is the combination of datasets obtained from different measurements with different settings (e.g. varying detector resolutions). Analyzing such datasets jointly, rather than independently or after naive merging, is essential for obtaining precise and unbiased estimates of the unknowns, but requires careful treatment of dataset heterogeneity and is computationally demanding. We present a generalized framework for simultaneously analyzing multiple heterogeneous datasets in the context of generative AI-based inverse problem solvers. Building on our recent Scalable Asynchronous Generative Inverse Problem Solver (SAGIPS) framework, we extend the well-established distributed data-parallel training paradigm to non-identically distributed datasets, where each dataset is controlled by the same set of unknown inference parameters but covers a different region of the available feature space. Each dataset is processed through its own forward operator and discriminator, providing complementary constraints that collectively guide a shared generator toward global parameter consistency. We validate the approach using a controlled setup inspired by a multi-detector scattering experiment. We provide numerical evidence that our framework is robust to different data fidelities, which arise from unknown detector systematics in the Rutherford experiment, and we show the scaling behavior on multi-GPU leadership computing systems. The results show that our approach is well suited for real-world multi-dataset analyses in which experimental conditions vary across measurements.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-28 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.26283 — 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 2026-10-17T15:17:44.890Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).