# Efficient Hyperparameter Importance Assessment for CNNs

Source: [Efficient Hyperparameter Importance Assessment for CNNs](<https://www.sota2.com/research/paper/68fa75411e209131cea66d98>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:10.357Z

Authors: Ruinan Wang, Ian Nabney, Mohammad Golbabaee

Published: 2024-10-11T15:47:46.000Z

## Abstract

Hyperparameter selection is an essential aspect of the machine learning pipeline, profoundly impacting models' robustness, stability, and generalization capabilities. Given the complex hyperparameter spaces associated with Neural Networks and the constraints of computational resources and time, optimizing all hyperparameters becomes impractical. In this context, leveraging hyperparameter importance assessment (HIA) can provide valuable guidance by narrowing down the search space. This enables machine learning practitioners to focus their optimization efforts on the hyperparameters with the most significant impact on model performance while conserving time and resources. This paper aims to quantify the importance weights of some hyperparameters in Convolutional Neural Networks (CNNs) with an algorithm called N-RReliefF, laying the groundwork for applying HIA methodologies in the Deep Learning field. We conduct an extensive study by training over ten thousand CNN models across ten popular image classification datasets, thereby acquiring a comprehensive dataset containing hyperparameter configuration instances and their corresponding performance metrics. It is demonstrated that among the investigated hyperparameters, the top five important hyperparameters of the CNN model are the number of convolutional layers, learning rate, dropout rate, optimizer and epoch.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.08920>)

[PDF](<https://arxiv.org/pdf/2410.08920.pdf>)
