Skip to yearly menu bar Skip to main content


Energy-Based Processes for Exchangeable Data

Mengjiao Yang · Bo Dai · Hanjun Dai · Dale Schuurmans


Keywords: [ Deep Generative Models ] [ Generative Models ] [ Representation Learning ] [ Probabilistic Inference - Models and Probabilistic Programming ]


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

Chat is not available.