Energy-Based Processes for Exchangeable Data
This addresses limitations in current set modeling approaches for applications like point cloud processing, though it appears incremental as an extension of energy-based models.
The paper tackled the problem of modeling exchangeable data like point clouds by introducing Energy-Based Processes (EBPs), which allow flexible distributions over sets without cardinality restrictions, and demonstrated state-of-the-art performance on tasks such as point cloud generation and classification.
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.