Metraipolis › archive › dc_2fc45b8b10cd

From Data to Program: Fast & Direct Generative Program Inference from Empirical Data — arXiv:2609.35348

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35348
License (as archived)
CC0-1.0
Archived
2026-10-07T21:03:28.723Z
SHA-256 of the archived text
8a6e595c2bcdfe7abc0e49e62b73ca6c2f8c4026749691bb6ccc8ac5c1e98e63
Stable URL of this page
https://metraipolis.com/documento/dc_2fc45b8b10cd

How to cite

From Data to Program: Fast & Direct Generative Program Inference from Empirical Data — arXiv:2609.35348 — arXiv (en), https://arxiv.org/abs/2609.35348 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fc45b8b10cd (Metraipolis archive dc_2fc45b8b10cd, sha256 8a6e595c2bcdfe7abc0e49e62b73ca6c2f8c4026749691bb6ccc8ac5c1e98e63)
BibTeX
@misc{dc2fc45b8b10cd,
  title = {From Data to Program: Fast & Direct Generative Program Inference from Empirical Data — arXiv:2609.35348},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35348},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fc45b8b10cd; sha256 8a6e595c2bcdfe7abc0e49e62b73ca6c2f8c4026749691bb6ccc8ac5c1e98e63},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35348. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Estimating probability densities from a finite set of samples typically requires dataset-specific model fitting. We introduce PRODiGI, a pretrained data-to-program model that infers an explicit, executable generative program in a single forward pass. Pretrained on synthetic datasets paired with their ground-truth programs, PRODiGI accommodates diverse generative families and data dimensionalities through template prediction and non-autoregressive program parameter decoding. Its inferred programs support direct sampling, density and score evaluation, and inspection independently of the pretrained model. We further introduce program-space fine-tuning, which refines differentiable program parameters by matching generated and empirical samples while keeping model parameters intact. Experiments show that PRODiGI achieves lower average density and score MAE than existing pretrained models, while offering multi-fold speedups over its closest competitors. Program-space fine-tuning further reduces generation MMD by 84%. By turning empirical data into explicit, reusable programs, PRODiGI introduces a new direction for fast, interpretable tabular generative modeling.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.35348 — 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 2026-10-07T20:29:03.321Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).