# ParaRNN: An Interpretable and Parallelizable Recurrent Neural Network for Time-Dependent Data

arXiv: https://arxiv.org/abs/2605.02692 · HTML: https://mlsanity.com/paper/2605.02692/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 70 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 1 of 1)

- [Approximation Bounds for Recurrent Neural Networks with Application to Regression](https://mlsanity.com/paper/2409.05577/) (2024)

## Abstract (arXiv)

The proliferation of large-scale and structurally complex data has spurred the integration of machine learning methods into statistical modeling. Recurrent neural networks (RNNs), a foundational class of models for time-dependent data, can be viewed as nonlinear extensions of classical autoregressive moving average models. Despite their flexibility and empirical success in machine learning, RNNs often suffer from limited interpretability and slow training, which hinders their use in statistics. This paper proposes the Parallelized RNN (ParaRNN), a novel model composed of multiple small recurrent units. ParaRNN admits an additive representation that decouples recurrent dynamics into interpretable components, whose behavior can be characterized through recurrence features. This interpretability enables its applications in nonparametric regression for time-dependent data, while the design also allows efficient parallelization. The approximation capacity and non-asymptotic prediction error bounds in a nonparametric regression setting are established for ParaRNN. Empirical results on three sequential modeling tasks further demonstrate that ParaRNN achieves performance comparable to vanilla RNNs while offering improved interpretability and efficiency.