A Statistical Framework for Model Selection in LSTM Networks

TL;DR

This paper introduces a unified statistical framework for systematic model selection in LSTM networks, addressing hyperparameter tuning, architecture, and regularization with improved efficiency and applicability across biomedical data.

Contribution

It extends classical model selection methods to LSTM networks, incorporating penalized likelihoods, thresholding, and efficient estimation strategies.

Findings

Demonstrates improved model selection performance on biomedical datasets

Provides a flexible framework adaptable to various sequential data applications

Achieves more systematic and less heuristic model tuning in LSTM networks

Abstract

Long Short-Term Memory (LSTM) 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.