arbiter
JournalsPricingAccount

A Statistical Framework for Model Selection in LSTM Networks

Fahad Mostafa

Model Assisted Statistics and Applications2026https://doi.org/10.1177/15741699251410081article
ABDC C
Weight
0.50

What the paper says

Long Short-Term Memory neural network models have become the cornerstone for sequential data modeling in numerous applications, ranging from natural language processing to time series forecasting. Despite their success, the problem of model selection, including hyperparameter tuning, architecture specification, and regularization choice remains largely heuristic and computationally expensive. In this paper, we propose a unified statistical framework for systematic model selection in LSTM networks. Our framework extends classical model selection ideas, such as information criteria and shrinkage estimation, to sequential neural networks. We define penalized likelihoods adapted to temporal structures, propose a generalized threshold approach for hidden state dynamics, and provide efficient estimation strategies using variational Bayes and approximate marginal likelihood methods. Several biomedical data centric examples demonstrate the flexibility and improved performance of the proposed framework.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1177/15741699251410081

Or copy a formatted citation

@article{fahad2026,
  title        = {{A Statistical Framework for Model Selection in LSTM Networks}},
  author       = {Fahad Mostafa},
  journal      = {Model Assisted Statistics and Applications},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.1177/15741699251410081},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

A Statistical Framework for Model Selection in LSTM Networks

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.