当前位置:
X-MOL 学术
›
arXiv.cs.LG
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Energy-Based Processes for Exchangeable Data
arXiv - CS - Machine Learning Pub Date : 2020-03-17 , DOI: arxiv-2003.07521 Mengjiao Yang, Bo Dai, Hanjun Dai, Dale Schuurmans
arXiv - CS - Machine Learning Pub Date : 2020-03-17 , DOI: arxiv-2003.07521 Mengjiao Yang, Bo Dai, Hanjun Dai, Dale Schuurmans
Recently there has been growing interest in modeling sets with
exchangeability such as point clouds. A shortcoming of current approaches is
that they restrict the cardinality of the sets considered or can only express
limited forms of distribution over unobserved data. To overcome these
limitations, we introduce Energy-Based Processes (EBPs), which extend energy
based models to exchangeable data while allowing neural network
parameterizations of the energy function. A key advantage of these models is
the ability to express more flexible distributions over sets without
restricting their cardinality. We develop an efficient training procedure for
EBPs that demonstrates state-of-the-art performance on a variety of tasks such
as point cloud generation, classification, denoising, and image completion.
中文翻译:
可交换数据的基于能量的过程
最近,人们对具有可交换性的建模集(例如点云)越来越感兴趣。当前方法的一个缺点是它们限制了所考虑集合的基数,或者只能表达对未观察数据的有限分布形式。为了克服这些限制,我们引入了基于能量的过程 (EBP),它将基于能量的模型扩展到可交换数据,同时允许能量函数的神经网络参数化。这些模型的一个关键优势是能够在不限制其基数的情况下表达更灵活的集合分布。我们为 EBP 开发了一种高效的训练程序,该程序在点云生成、分类、去噪和图像完成等各种任务上展示了最先进的性能。
更新日期:2020-07-09
中文翻译:
可交换数据的基于能量的过程
最近,人们对具有可交换性的建模集(例如点云)越来越感兴趣。当前方法的一个缺点是它们限制了所考虑集合的基数,或者只能表达对未观察数据的有限分布形式。为了克服这些限制,我们引入了基于能量的过程 (EBP),它将基于能量的模型扩展到可交换数据,同时允许能量函数的神经网络参数化。这些模型的一个关键优势是能够在不限制其基数的情况下表达更灵活的集合分布。我们为 EBP 开发了一种高效的训练程序,该程序在点云生成、分类、去噪和图像完成等各种任务上展示了最先进的性能。