# Deep Sigma Point Processes

arXiv: https://arxiv.org/abs/2002.09112 · HTML: https://mlsanity.com/paper/2002.09112/

## Key facts

- Cited by 16 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 21 Feb 2020.

## Built on by (most cited first, 16 of 16)

- [Stochastic Process Learning via Operator Flow Matching](https://mlsanity.com/paper/2501.04126/) (2025)
- [Universal Functional Regression with Neural Operator Flows](https://mlsanity.com/paper/2404.02986/) (2024)
- [Scalable Cross Validation Losses for Gaussian Process Models](https://mlsanity.com/paper/2105.11535/) (2021)
- [Bayesian Meta-Learning Through Variational Gaussian Processes](https://mlsanity.com/paper/2110.11044/) (2021)
- [Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecasting](https://mlsanity.com/paper/2212.10306/) (2022)
- [dynoGP: Deep Gaussian Processes for dynamic system identification](https://mlsanity.com/paper/2502.05620/) (2025)
- [Uncertainty-aware Remaining Useful Life predictor](https://mlsanity.com/paper/2104.03613/) (2021)
- [Amortized Variational Inference for Deep Gaussian Processes](https://mlsanity.com/paper/2409.12301/) (2024)
- [Evaluating Uncertainty in Deep Gaussian Processes](https://mlsanity.com/paper/2504.17719/) (2025)
- [Photoelectric Factor Prediction Using Automated Learning and Uncertainty Quantification](https://mlsanity.com/paper/2206.08950/) (2022)
- [Gradient-enhanced deep Gaussian processes for multifidelity modelling](https://mlsanity.com/paper/2402.16059/) (2024)
- [Deep Q-Exponential Processes](https://mlsanity.com/paper/2410.22119/) (2024)
- [A Physics-Guided Probabilistic Surrogate Modeling Framework for Digital Twins of Underwater Radiated Noise](https://mlsanity.com/paper/2509.25730/) (2025)
- [Deep Gaussian Process Proximal Policy Optimization](https://mlsanity.com/paper/2511.18214/) (2025)
- [Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding](https://mlsanity.com/paper/2605.08446/) (2026)
- [Deep Sigma Point Processes for RCS Modeling in Spaceborne SAR Imagery](https://mlsanity.com/paper/2607.21745/) (2026)

## Abstract (arXiv)

We introduce Deep Sigma Point Processes, a class of parametric models inspired by the compositional structure of Deep Gaussian Processes (DGPs). Deep Sigma Point Processes (DSPPs) retain many of the attractive features of (variational) DGPs, including mini-batch training and predictive uncertainty that is controlled by kernel basis functions. Importantly, since DSPPs admit a simple maximum likelihood inference procedure, the resulting predictive distributions are not degraded by any posterior approximations. In an extensive empirical comparison on univariate and multivariate regression tasks we find that the resulting predictive distributions are significantly better calibrated than those obtained with other probabilistic methods for scalable regression, including variational DGPs--often by as much as a nat per datapoint.