基于能量的可交换数据处理
Energy-Based Processes for Exchangeable Data
摘要：
最近，人们对使用交换矩阵（如点云）对集进行建模的兴趣越来越大。目前的方法的一个缺点是，它们限制了所考虑的集合的基数，或者只能表示未观察到的数据的有限形式的分布。为了克服这些限制，我们引入基于能量的过程（EBP），它将基于能量的模型扩展到可交换的数据，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表达集合上更灵活的分布，而不限制它们的基数。我们为EBP开发了一个高效的训练程序，该程序在点云生成、分类、去噪和图像完成等各种任务上都表现出了最先进的性能。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
