Practical Integration via Separable Bijective Networks
Practical Integration via Separable Bijective Networks
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Christopher M. Bender;Patrick Emmanuel;M. Reiter;Junier B. Oliva
中科院分区：
文献类型：
--
作者：
Christopher M. Bender;Patrick Emmanuel;M. Reiter;Junier B. Oliva
神经网络使学习的示例能够学习，但是这些模型中的大多数都限于训练和评估有限的积分，并且不考虑对模型本地或本地分析的Hypervolume。因此可分离的网络可以通过在输入空间进行集成，以精确的估计量进行全面的估计器进行学习（或评估）。
Neural networks have enabled learning over examples that contain thousands of dimensions. However, most of these models are limited to training and evaluating on a finite collection of points and do not consider the hypervolume in which the data resides. Any analysis of the model’s local or global behavior is therefore limited to very expensive or imprecise estimators. We propose to formulate neural networks as a composition of a bijective (flow) network followed by a learnable, separable network. This construction allows for learning (or assessing) over full hypervolumes with precise estimators at tractable computational cost via integration over the input space. We develop the necessary machinery, propose several practical integrals to use during training, and demonstrate their utility.