# Uncertainty Prediction for Deep Sequential Regression Using Meta Models

arXiv: https://arxiv.org/abs/2007.01350 · HTML: https://mlsanity.com/paper/2007.01350/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data](https://mlsanity.com/paper/2310.16524/) (2023)
- [Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI](https://mlsanity.com/paper/2106.01410/) (2021)
- [Improving Adaptive Conformal Prediction Using Self-Supervised Learning](https://mlsanity.com/paper/2302.12238/) (2023)
- [Data-SUITE: Data-centric identification of in-distribution incongruous examples](https://mlsanity.com/paper/2202.08836/) (2022)
- [Quantifying and Improving Adaptivity in Conformal Prediction through Input Transformations](https://mlsanity.com/paper/2511.11472/) (2025)
- [Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better](https://mlsanity.com/paper/2601.21455/) (2026)

## Abstract (arXiv)

Generating high quality uncertainty estimates for sequential regression, particularly deep recurrent networks, remains a challenging and open problem. Existing approaches often make restrictive assumptions (such as stationarity) yet still perform poorly in practice, particularly in presence of real world non-stationary signals and drift. This paper describes a flexible method that can generate symmetric and asymmetric uncertainty estimates, makes no assumptions about stationarity, and outperforms competitive baselines on both drift and non drift scenarios. This work helps make sequential regression more effective and practical for use in real-world applications, and is a powerful new addition to the modeling toolbox for sequential uncertainty quantification in general.