# Recurrent Neural Processes

arXiv: https://arxiv.org/abs/1906.05915 · HTML: https://mlsanity.com/paper/1906.05915/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2019.

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

- [Latent Bottlenecked Attentive Neural Processes](https://mlsanity.com/paper/2211.08458/) (2022)
- [The Neural Process Family: Survey, Applications and Perspectives](https://mlsanity.com/paper/2209.00517/) (2022)
- [Memory Efficient Neural Processes via Constant Memory Attention Block](https://mlsanity.com/paper/2305.14567/) (2023)
- [Social Processes: Self-Supervised Meta-Learning over Conversational Groups for Forecasting Nonverbal Social Cues](https://mlsanity.com/paper/2107.13576/) (2021)
- [Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies](https://mlsanity.com/paper/2310.10500/) (2023)
- [GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data](https://mlsanity.com/paper/2106.04967/) (2021)
- [Meta-Learning for Koopman Spectral Analysis with Short Time-series](https://mlsanity.com/paper/2102.04683/) (2021)
- [Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation](https://mlsanity.com/paper/2408.02685/) (2024)
- [How to Tame Your LLM: Semantic Collapse in Continuous Systems](https://mlsanity.com/paper/2512.05162/) (2025)
- [NPBoost: Neural Processes with Gradient-Boosted Fixed Effects](https://mlsanity.com/paper/2609.28122/) (2026)

## Abstract (arXiv)

We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models. RNPs model the state space with Neural Processes. Given time series observed on fast real-world time scales but containing slow long-term variabilities, RNPs may derive appropriate slow latent time scales. They do so in an efficient manner by establishing conditional independence among subsequences of the time series. Our theoretically grounded framework for stochastic processes expands the applicability of NPs while retaining their benefits of flexibility, uncertainty estimation, and favorable runtime with respect to Gaussian Processes (GPs). We demonstrate that state spaces learned by RNPs benefit predictive performance on real-world time-series data and nonlinear system identification, even in the case of limited data availability.