Saved in:
Bibliographic Details
Main Authors: You, Jiang, Cela, Arben, Natowicz, René, Ouanounou, Jacob, Siarry, Patrick
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.02438
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917793663811584
author You, Jiang
Cela, Arben
Natowicz, René
Ouanounou, Jacob
Siarry, Patrick
author_facet You, Jiang
Cela, Arben
Natowicz, René
Ouanounou, Jacob
Siarry, Patrick
contents Training deep models for time series forecasting is a critical task with an inherent challenge of time complexity. While current methods generally ensure linear time complexity, our observations on temporal redundancy show that high-level features are learned 98.44\% slower than low-level features. To address this issue, we introduce a new exponentially weighted stochastic gradient descent algorithm designed to achieve constant time complexity in deep learning models. We prove that the theoretical complexity of this learning method is constant. Evaluation of this method on Kernel U-Net (K-U-Net) on synthetic datasets shows a significant reduction in complexity while improving the accuracy of the test set.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02438
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning K-U-Net with constant complexity: An Application to time series forecasting
You, Jiang
Cela, Arben
Natowicz, René
Ouanounou, Jacob
Siarry, Patrick
Machine Learning
Training deep models for time series forecasting is a critical task with an inherent challenge of time complexity. While current methods generally ensure linear time complexity, our observations on temporal redundancy show that high-level features are learned 98.44\% slower than low-level features. To address this issue, we introduce a new exponentially weighted stochastic gradient descent algorithm designed to achieve constant time complexity in deep learning models. We prove that the theoretical complexity of this learning method is constant. Evaluation of this method on Kernel U-Net (K-U-Net) on synthetic datasets shows a significant reduction in complexity while improving the accuracy of the test set.
title Learning K-U-Net with constant complexity: An Application to time series forecasting
topic Machine Learning
url https://arxiv.org/abs/2410.02438