# Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions

arXiv: https://arxiv.org/abs/2006.13707 · HTML: https://mlsanity.com/paper/2006.13707/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2020.

## Built on by (most cited first, 18 of 18)

- [Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis](https://mlsanity.com/paper/2210.04714/) (2022)
- [Quantifying Uncertainty in Deep Spatiotemporal Forecasting](https://mlsanity.com/paper/2105.11982/) (2021)
- [HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks](https://mlsanity.com/paper/2102.02515/) (2021)
- [Copula Conformal Prediction for Multi-step Time Series Forecasting](https://mlsanity.com/paper/2212.03281/) (2022)
- [Conformal Prediction with Temporal Quantile Adjustments](https://mlsanity.com/paper/2205.09940/) (2022)
- [Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models](https://mlsanity.com/paper/2405.16475/) (2024)
- [Conformal Methods for Quantifying Uncertainty in Spatiotemporal Data: A Survey](https://mlsanity.com/paper/2209.03580/) (2022)
- [Quantifying Epistemic Uncertainty in Deep Learning](https://mlsanity.com/paper/2110.12122/) (2021)
- [Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks](https://mlsanity.com/paper/2306.05674/) (2023)
- [What's Behind the Mask: Estimating Uncertainty in Image-to-Image Problems](https://mlsanity.com/paper/2211.15211/) (2022)
- [Uncertainty-aware Traffic Prediction under Missing Data](https://mlsanity.com/paper/2309.06800/) (2023)
- [Step-resolved data attribution for looped transformers](https://mlsanity.com/paper/2602.10097/) (2026)
- [JAPAN: Joint Adaptive Prediction Areas with Normalising-Flows](https://mlsanity.com/paper/2505.23196/) (2025)
- [JANET: Joint Adaptive predictioN-region Estimation for Time-series](https://mlsanity.com/paper/2407.06390/) (2024)
- [Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecasting](https://mlsanity.com/paper/2302.11078/) (2023)
- [Monitoring Time Series With Missing Values: a Deep Probabilistic Approach](https://mlsanity.com/paper/2203.04916/) (2022)
- [Partially stochastic deep learning with uncertainty quantification for model predictive heating control](https://mlsanity.com/paper/2504.03350/) (2025)
- [Bounded-Abstention Multi-horizon Time-series Forecasting](https://mlsanity.com/paper/2602.04714/) (2026)

## Abstract (arXiv)

Recurrent neural networks (RNNs) are instrumental in modelling sequential and time-series data. Yet, when using RNNs to inform decision-making, predictions by themselves are not sufficient; we also need estimates of predictive uncertainty. Existing approaches for uncertainty quantification in RNNs are based predominantly on Bayesian methods; these are computationally prohibitive, and require major alterations to the RNN architecture and training. Capitalizing on ideas from classical jackknife resampling, we develop a frequentist alternative that: (a) does not interfere with model training or compromise its accuracy, (b) applies to any RNN architecture, and (c) provides theoretical coverage guarantees on the estimated uncertainty intervals. Our method derives predictive uncertainty from the variability of the (jackknife) sampling distribution of the RNN outputs, which is estimated by repeatedly deleting blocks of (temporally-correlated) training data, and collecting the predictions of the RNN re-trained on the remaining data. To avoid exhaustive re-training, we utilize influence functions to estimate the effect of removing training data blocks on the learned RNN parameters. Using data from a critical care setting, we demonstrate the utility of uncertainty quantification in sequential decision-making.