# Energy-Based Processes for Exchangeable Data

arXiv: https://arxiv.org/abs/2003.07521 · HTML: https://mlsanity.com/paper/2003.07521/

## Key facts

- Cited by 10 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 17 Mar 2020.

## Built on by (most cited first, 10 of 10)

- [Learning to Generate Realistic LiDAR Point Clouds](https://mlsanity.com/paper/2209.03954/) (2022)
- [SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data](https://mlsanity.com/paper/2103.15619/) (2021)
- [Deep Gaussian Processes: A Survey](https://mlsanity.com/paper/2106.12135/) (2021)
- [Do Finetti: On Causal Effects for Exchangeable Data](https://mlsanity.com/paper/2405.18836/) (2024)
- [Energy-Based Models for Functional Data using Path Measure Tilting](https://mlsanity.com/paper/2202.01929/) (2022)
- [Spectral Convolutional Conditional Neural Processes](https://mlsanity.com/paper/2404.13182/) (2024)
- [Partially Observed Exchangeable Modeling](https://mlsanity.com/paper/2102.06083/) (2021)
- [Adaptive Conditional Quantile Neural Processes](https://mlsanity.com/paper/2305.18777/) (2023)
- [Exchangeability-Aware Sum-Product Networks](https://mlsanity.com/paper/2110.05165/) (2021)
- [Deep Optimal Sensor Placement for Black Box Stochastic Simulations](https://mlsanity.com/paper/2410.12036/) (2024)

## Abstract (arXiv)

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.