Abstract:Classical deep learning typically operates on individual cases. Despite its success, real-world usage often requires repeated inference to estimate statistical quantities for complex decision-making tasks involving uncertainty or extreme-value analysis, resulting in substantial latency. We introduce neural statistical functions, a new family of models learned from pre-trained single-sample predictors and scattered data samples, which can directly infer statistics over continuous operating condition ranges without explicit sampling. By introducing the notion of prefix statistics, we transform and unify diverse statistical functions (e.g., integrals, quantiles, and maxima) into an interval-conditional framework, in which a principled identity between the prefix statistics and the individual-case regression serves as the learning objective. Neural statistical functions achieve strong performance in estimating essential statistics of complex physical processes, including accumulated energy in dynamical systems, quantiles of aerodynamic responses, and maximum stress in crash processes, while achieving up to a 100$\times$ reduction in model evaluations.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.11327 [cs.LG] |
| (or arXiv:2605.11327v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.11327 arXiv-issued DOI via DataCite (pending registration) |
From: Daniel Xu [view email]
[v1]
Mon, 11 May 2026 23:25:56 UTC (1,733 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。