Saved in:
Bibliographic Details
Main Author: Khatri, Alizishaan Anwar Hussein
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.16334
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910141928964096
author Khatri, Alizishaan Anwar Hussein
author_facet Khatri, Alizishaan Anwar Hussein
contents The use of Deep Neural Network based systems in the real world is growing. They have achieved state-of-the-art performance on many image, speech and text datasets. They have been shown to be powerful systems that are capable of learning detailed relationships and abstractions from the data. This is a double-edged sword which makes such systems vulnerable to learning the noise in the training set, thereby negatively impacting performance. This is also known as the problem of \emph{overfitting} or \emph{poor generalization}. In a practical setting, analysts typically have limited data to build models that must generalize to unseen data. In this work, we explore the use of a differential-privacy based approach to improve generalization in Deep Neural Networks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16334
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Preventing overfitting in deep learning using differential privacy
Khatri, Alizishaan Anwar Hussein
Machine Learning
Artificial Intelligence
The use of Deep Neural Network based systems in the real world is growing. They have achieved state-of-the-art performance on many image, speech and text datasets. They have been shown to be powerful systems that are capable of learning detailed relationships and abstractions from the data. This is a double-edged sword which makes such systems vulnerable to learning the noise in the training set, thereby negatively impacting performance. This is also known as the problem of \emph{overfitting} or \emph{poor generalization}. In a practical setting, analysts typically have limited data to build models that must generalize to unseen data. In this work, we explore the use of a differential-privacy based approach to improve generalization in Deep Neural Networks.
title Preventing overfitting in deep learning using differential privacy
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2604.16334