# Informative Neural Ensemble Kalman Learning

arXiv: https://arxiv.org/abs/2008.09915 · HTML: https://mlsanity.com/paper/2008.09915/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Aug 2020.

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

- [Combining data assimilation and machine learning to estimate parameters of a convective-scale model](https://mlsanity.com/paper/2109.02953/) (2021)
- [Learn Like The Pro: Norms from Theory to Size Neural Computation](https://mlsanity.com/paper/2106.11409/) (2021)
- [Downscaling Extreme Rainfall Using Physical-Statistical Generative Adversarial Learning](https://mlsanity.com/paper/2212.01446/) (2022)
- [Learning a Stochastic Differential Equation Model of Tropical Cyclone Intensification from Reanalysis and Observational Data](https://mlsanity.com/paper/2601.08116/) (2026)
- [Multirotor Ensemble Model Predictive Control I: Simulation Experiments](https://mlsanity.com/paper/2305.12625/) (2023)
- [The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual Learning](https://mlsanity.com/paper/2610.03225/) (2026)

## Abstract (arXiv)

In stochastic systems, informative approaches select key measurement or decision variables that maximize information gain to enhance the efficacy of model-related inferences. Neural Learning also embodies stochastic dynamics, but informative Learning is less developed. Here, we propose Informative Ensemble Kalman Learning, which replaces backpropagation with an adaptive Ensemble Kalman Filter to quantify uncertainty and enables maximizing information gain during Learning. After demonstrating Ensemble Kalman Learning's competitive performance on standard datasets, we apply the informative approach to neural structure learning. In particular, we show that when trained from the Lorenz-63 system's simulations, the efficaciously learned structure recovers the dynamical equations. To the best of our knowledge, Informative Ensemble Kalman Learning is new. Results suggest that this approach to optimized Learning is promising.