论文标题
关于贝叶斯深网的概括用于多级分类
On the generalization of bayesian deep nets for multi-class classification
论文作者
论文摘要
广泛研究了评估真实风险和经验风险之间差异的概括范围。但是，为了获得边界，当前技术使用严格的假设，例如统一边界或Lipschitz损失函数。为了避免这些假设，在本文中，我们提出了一个新的概括，通过利用log-sobolev不平等的合同性来限制贝叶斯深网。使用这些不平等，将概括性结合增加了额外的损耗型范围项，这在直觉上是模型复杂性的替代物。从经验上讲，我们使用不同的深网分析了此损失梯度规范项的影响。
Generalization bounds which assess the difference between the true risk and the empirical risk have been studied extensively. However, to obtain bounds, current techniques use strict assumptions such as a uniformly bounded or a Lipschitz loss function. To avoid these assumptions, in this paper, we propose a new generalization bound for Bayesian deep nets by exploiting the contractivity of the Log-Sobolev inequalities. Using these inequalities adds an additional loss-gradient norm term to the generalization bound, which is intuitively a surrogate of the model complexity. Empirically, we analyze the affect of this loss-gradient norm term using different deep nets.
