Metraipolis › archive › dc_0f378b39e366
SelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted Networks — arXiv:2610.21950
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.21950
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:25:17.864Z
- SHA-256 of the archived text
db62b9dca73bdb8bdda85497ebb686f706b44669f070ab7376ae3805b2405fda- Stable URL of this page
https://metraipolis.com/documento/dc_0f378b39e366
How to cite
SelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted Networks — arXiv:2610.21950 — arXiv (en), https://arxiv.org/abs/2610.21950 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f378b39e366 (Metraipolis archive dc_0f378b39e366, sha256 db62b9dca73bdb8bdda85497ebb686f706b44669f070ab7376ae3805b2405fda)
BibTeX
@misc{dc0f378b39e366,
title = {SelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted Networks — arXiv:2610.21950},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.21950},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f378b39e366; sha256 db62b9dca73bdb8bdda85497ebb686f706b44669f070ab7376ae3805b2405fda},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21950. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Tabular foundation models based on prior-data fitted networks (PFNs) predict on a new data set in a single forward pass, but they cannot report which inputs their predictions depend on. We propose SelectPFN, a PFN that performs Bayesian variable selection and prediction jointly for sparse nonlinear regression. In one forward pass it returns posterior inclusion probabilities for every variable, and its predictions are computed from sampled subsets only, so excluded variables provably cannot affect them; we show this is exactly what the Bayesian model prescribes. The network is pretrained once on synthetic tasks from a meta-prior built around a group spike-and-slab sparse-input neural network. Column-permutation equivariance combined with random interleaving of original and knockoff columns yields knockoff statistics with exact finite-sample false discovery rate control, even when the meta-prior is wrong. We develop theory for amortized selection: a Bayes-regret bound for the amortized median probability model, a characterization showing that the information needed to detect a variable grows like $(2/\lambda)\log(1/\omega)$ in the prior weight $\omega$ of structures that can use it, where $\lambda\le1$ is an efficiency, and a negative result showing that average-case training does not transfer to frequentist guarantees at a fixed truth. On out-of-prior nonlinear designs with p up to 500, SelectPFN improves the area under the precision-recall curve by 0.23-0.28 over the lasso, BART, DART, LassoNet and a group-penalized sparse neural network, at a false discovery proportion of about 0.07 and 0.04 seconds per data set. The advantage persists on real covariate matrices, and, as the theory predicts, detection of interaction-only variables rises monotonically with their prior weight. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.21950 — 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 2026-10-16T08:48:02.926Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).