PRODiGI:从经验数据快速直接推断生成式程序的新模型
From Data to Program: Fast & Direct Generative Program Inference from Empirical Data
AI 导读
研究者提出预训练数据到程序模型 PRODiGI,单次前向传播即可从有限样本推断出显式可执行的生成程序,无需针对数据集拟合。其程序空间微调方法 PRODiTi-FT 在密度与分数指标上优于现有预训练模型,速度较最近竞争者提升数倍,微调还可将生成 MMD 降低 90%。该模型无需依赖预训练模型即可直接采样、评估密度并检查程序,为可解释的表格生成建模提供新方向。
正文 · 原文
Abstract: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 maximizing the likelihood of empirical data while keeping model parameters intact. Experiments show that PRODiGI-FT achieves better density and score metrics than existing pretrained models, while offering multi-fold speedups over its closest competitors. Program-space fine-tuning further reduces generation MMD by 90%. By turning empirical data into explicit, reusable programs, PRODiGI introduces a new direction for fast, interpretable tabular generative modeling.
| Comments: | 63 pages, 20 figures, |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.35348 [cs.LG] |
| (or arXiv:2609.35348v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.35348 arXiv-issued DOI via DataCite |
Submission history
From: Simon Klüttermann [view email]
[v1]
Mon, 28 Sep 2026 15:01:54 UTC (3,833 KB)
[v2]
Fri, 13 Nov 2026 17:09:27 UTC (3,968 KB)
来源:arXiv cs.AI · arxiv.org