贝叶斯神经网络何时采样足够？具有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
浏览论文内容
中文总结 AI 辅助
该研究提出用置信序列动态确定贝叶斯神经网络的采样数量，以保证统计决策，实验显示其能高效分配计算预算并降低延迟。
中文摘要 AI 辅助
贝叶斯神经网络的预测通常通过对每个输入使用固定数量的蒙特卡洛采样来近似，而不控制这种有限采样带来的误差。我们提出使用置信序列来动态确定所需的采样数量，同时保持统计保证。我们考虑了预测概率的多种使用方式，包括识别最可能的类别、近似完整的预测分布以及解决概率阈值决策问题。当能够以所需的保证做出相应决策时，采样停止。实验表明，该方法能高效分配计算预算，为模糊输入分配更多采样，为简单输入分配更少采样，同时保持可靠的决策，并相对于固定的蒙特卡洛预算降低了整体延迟。
英文摘要
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.
发表机构
- Eindhoven University of Technology（埃因霍温理工大学）
机构由 AI 辅助整理，请以论文原文为准。
