Timezone: »

Energy-Based Processes for Exchangeable Data
Mengjiao Yang · Bo Dai · Hanjun Dai · Dale Schuurmans

Thu Jul 16 09:00 AM -- 09:45 AM & Thu Jul 16 11:00 PM -- 11:45 PM (PDT) @ Virtual #None

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

Author Information

Mengjiao Yang (Google Brain)
Bo Dai (Google Brain)
Hanjun Dai (Google Brain)
Dale Schuurmans (Google / University of Alberta)

More from the Same Authors