研究人员在组合高斯过程（GPs）中发现了一个临界阈值，该阈值决定了深度模型中的行为是退化还是非平凡的。研究确定了一个尖锐的带宽阈值 $r_c(d) = \Theta(\sqrt{d})$，高于该阈值，GP先验收敛到常数函数。低于该阈值，先验收敛到非高斯、非退化的分布，为深度贝叶斯网络提供了更有用的概率模型。 AI
影响 确定了深度高斯过程的临界阈值，有可能在深度学习架构中实现更鲁棒的贝叶斯建模。
排序理由 该集群包含一篇详细介绍机器学习新理论发现的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.08218v1 Announce Type: cross Abstract: Compositional priors describe the generic properties of layered functions in deep Bayesian models, where deep neural networks with random weights are a canonical example.In the wide-network limit, the prior is a Gaussian process w…
Compositional priors describe the generic properties of layered functions in deep Bayesian models, where deep neural networks with random weights are a canonical example.In the wide-network limit, the prior is a Gaussian process with a depth-dependent kernel, and its behaviour as…