Enregistré dans:
Détails bibliographiques
Auteur principal: Landsgesell, Jonas
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2601.05683
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908754885214208
author Landsgesell, Jonas
author_facet Landsgesell, Jonas
contents Non-parametric distributional regression has achieved significant milestones in recent years. Among these, the Tabular Prior-Data Fitted Network (TabPFN) has demonstrated state-of-the-art performance on various benchmarks. However, a challenge remains in extending these grid-based approaches to a truly multivariate setting. In a naive non-parametric discretization with $N$ bins per dimension, the complexity of an explicit joint grid scales exponentially and the paramer count of the neural networks rise sharply. This scaling is particularly detrimental in low-data regimes, as the final projection layer would require many parameters, leading to severe overfitting and intractability.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05683
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Joint Optimization of Neural Autoregressors via Scoring rules
Landsgesell, Jonas
Soft Condensed Matter
Artificial Intelligence
Non-parametric distributional regression has achieved significant milestones in recent years. Among these, the Tabular Prior-Data Fitted Network (TabPFN) has demonstrated state-of-the-art performance on various benchmarks. However, a challenge remains in extending these grid-based approaches to a truly multivariate setting. In a naive non-parametric discretization with $N$ bins per dimension, the complexity of an explicit joint grid scales exponentially and the paramer count of the neural networks rise sharply. This scaling is particularly detrimental in low-data regimes, as the final projection layer would require many parameters, leading to severe overfitting and intractability.
title Joint Optimization of Neural Autoregressors via Scoring rules
topic Soft Condensed Matter
Artificial Intelligence
url https://arxiv.org/abs/2601.05683