arXiv：cs.AI· Fabian Denoodt, Sibylle Hess·· 3 小时前
贝叶斯神经网络何时采样足够？带统计保证的自适应推理时间
When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees
AI 导读
研究者提出用置信序列（confidence sequences）动态决定贝叶斯神经网络每个输入所需的 Monte Carlo 采样数，并在最可能类别识别、完整预测分布逼近和概率阈值决策三类任务上维持统计保证。实验显示该方法会把更多采样分配给模糊输入、给简单输入更少采样，在保持决策可靠的同时降低整体延迟。该工作发表于 NeurIPS 2026 Workshop: E-Values。
正文
Abstract:Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, without controlling the resulting error that comes from this finite sample. We propose the use of confidence sequences to dynamically determine how many samples are needed while maintaining statistical guarantees. We consider several ways in which predictive probabilities are used, including identifying the most likely class, approximating the full predictive distribution, and resolving probability-threshold decisions. Sampling stops once the corresponding decision can be made with the desired guarantee. Experiments show that the method allocates the computational budget efficiently, assigning more samples to ambiguous inputs than to easy inputs while preserving reliable decisions and reducing overall latency relative to a fixed Monte Carlo budget.
| Comments: | 40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: E-Values: From Statistics to ML |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.12212 [cs.AI] |
| (or arXiv:2610.12212v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12212 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fabian Denoodt [view email]
[v1]
Thu, 8 Oct 2026 16:01:08 UTC (204 KB)
来源：arXiv：cs.AI · arxiv.org