Towards black-box parameter estimation

Amanda Lenzi () and Haavard Rue
Additional contact information
Amanda Lenzi: University of Edinburgh
Haavard Rue: King Abdullah University of Science and Technology

Computational Statistics, 2025, vol. 40, issue 8, No 11, 4307-4329

Abstract: Abstract Deep learning algorithms have recently been shown to be a successful tool in estimating parameters of statistical models for which simulation is easy, but likelihood computation is challenging. This is achieved by sampling a large number of parameter values from a distribution, which is typically chosen to be non-informative and cover as much of the parameter space as possible. However, for high-dimensional and large parameter spaces, covering all possible reasonable parameter values is infeasible. We propose a new sequential training procedure that reduces simulation cost and guides simulations toward the region of high parameter density based on estimates of the neural network and the observed data. Our following proposal aims to fit time series models to newly collected data at no cost using a pre-trained neural network with simulated time series of a fixed length. These approaches can successfully estimate and quantify the uncertainty of parameters from non-Gaussian models with complex spatial and temporal dependencies. The success of our methods is a first step towards a fully flexible automatic black-box estimation framework.

Keywords: Deep neural networks; Sequential; Time-series; Simulation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s00180-025-01623-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:compst:v:40:y:2025:i:8:d:10.1007_s00180-025-01623-4

Ordering information: This journal article can be ordered from
http://www.springer.com/statistics/journal/180/PS2

DOI: 10.1007/s00180-025-01623-4

Access Statistics for this article

Computational Statistics is currently edited by Wataru Sakamoto, Ricardo Cao and Jürgen Symanzik

More articles in Computational Statistics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().