用截断正态分布更精准估计贝叶斯神经网络深度
Improved Depth Estimation of Bayesian Neural Networks
- 用离散截断正态分布独立学习深度均值与方差
- 在螺旋数据集上提升测试准确率并降低深度估计方差
- 适合关注模型深度建模与不确定性分析的研究者
本文改进了Nazareth和Blei（2022）关于贝叶斯神经网络深度估计的工作。提出在网络深度上使用离散截断正态分布，可独立学习其均值与方差。通过最小化变分自由能推断后验分布，实现模型复杂度与准确率的平衡。实验显示该方法在螺旋数据集上提升了测试准确率，并显著降低了后验深度估计的方差。
原文摘要 · Abstract (English)
This paper proposes improvements over earlier work by Nazareth and Blei (2022) for estimating the depth of Bayesian neural networks. Here, we propose a discrete truncated normal distribution over the network depth to independently learn its mean and variance. Posterior distributions are inferred by minimizing the variational free energy, which balances the model complexity and accuracy. Our method improves test accuracy on the spiral data set and reduces the variance in posterior depth estimates.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。