# Streaming Gaussian Dirichlet Random Fields for Spatial Predictions of High Dimensional Categorical Observations

arXiv: https://arxiv.org/abs/2402.15359 · HTML: https://mlsanity.com/paper/2402.15359/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 23 Feb 2024.

## Builds on (most cited first, 12 of 12)

- [Black Box Variational Inference](https://mlsanity.com/paper/1401.0118/) (2013)
- [Streaming Variational Bayes](https://mlsanity.com/paper/1307.6769/) (2013)
- [Streaming Sparse Gaussian Process Approximations](https://mlsanity.com/paper/1705.07131/) (2017)
- [WHOI-Plankton- A Large Scale Fine Grained Visual Recognition Benchmark Dataset for Plankton Classification](https://mlsanity.com/paper/1510.00745/) (2015)
- [Meta-Learning Priors for Safe Bayesian Optimization](https://mlsanity.com/paper/2210.00762/) (2022)
- [CUREE: A Curious Underwater Robot for Ecosystem Exploration](https://mlsanity.com/paper/2303.03943/) (2023)
- [Information-Guided Robotic Maximum Seek-and-Sample in Partially Observable Continuous Environments](https://mlsanity.com/paper/1909.12216/) (2019)
- [Multi-Robot Distributed Semantic Mapping in Unfamiliar Environments through Online Matching of Learned Representations](https://mlsanity.com/paper/2103.14805/) (2021)
- [Gibbs Sampling Strategies for Semantic Perception of Streaming Video Data](https://mlsanity.com/paper/1509.03242/) (2015)
- [Phytoplankton Hotspot Prediction With an Unsupervised Spatial Community Model](https://mlsanity.com/paper/1703.07309/) (2017)
- [Gaussian-Dirichlet Random Fields for Inference over High Dimensional Categorical Observations](https://mlsanity.com/paper/2003.12120/) (2020)
- [Informative Planning in the Presence of Outliers](https://mlsanity.com/paper/2111.01822/) (2021)

## Abstract (arXiv)

We present the Streaming Gaussian Dirichlet Random Field (S-GDRF) model, a novel approach for modeling a stream of spatiotemporally distributed, sparse, high-dimensional categorical observations. The proposed approach efficiently learns global and local patterns in spatiotemporal data, allowing for fast inference and querying with a bounded time complexity. Using a high-resolution data series of plankton images classified with a neural network, we demonstrate the ability of the approach to make more accurate predictions compared to a Variational Gaussian Process (VGP), and to learn a predictive distribution of observations from streaming categorical data. S-GDRFs open the door to enabling efficient informative path planning over high-dimensional categorical observations, which until now has not been feasible.