LETS Forecast: Learning Embedology for Time Series Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Majeedi, Abrar, Gajjala, Viswanatha Reddy, GNVV, Satya Sai Srinath Namburi, Elkordi, Nada Magdi, Li, Yin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910252814827520
author Majeedi, Abrar
Gajjala, Viswanatha Reddy
GNVV, Satya Sai Srinath Namburi
Elkordi, Nada Magdi
Li, Yin
author_facet Majeedi, Abrar
Gajjala, Viswanatha Reddy
GNVV, Satya Sai Srinath Namburi
Elkordi, Nada Magdi
Li, Yin
contents Real-world time series are often governed by complex nonlinear dynamics. Understanding these underlying dynamics is crucial for precise future prediction. While deep learning has achieved major success in time series forecasting, many existing approaches do not explicitly model the dynamics. To bridge this gap, we introduce DeepEDM, a framework that integrates nonlinear dynamical systems modeling with deep neural networks. Inspired by empirical dynamic modeling (EDM) and rooted in Takens' theorem, DeepEDM presents a novel deep model that learns a latent space from time-delayed embeddings, and employs kernel regression to approximate the underlying dynamics, while leveraging efficient implementation of softmax attention and allowing for accurate prediction of future time steps. To evaluate our method, we conduct comprehensive experiments on synthetic data of nonlinear dynamical systems as well as real-world time series across domains. Our results show that DeepEDM is robust to input noise, and outperforms state-of-the-art methods in forecasting accuracy. Our code is available at: https://abrarmajeedi.github.io/deep_edm.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06454
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LETS Forecast: Learning Embedology for Time Series Forecasting
Majeedi, Abrar
Gajjala, Viswanatha Reddy
GNVV, Satya Sai Srinath Namburi
Elkordi, Nada Magdi
Li, Yin
Machine Learning
Artificial Intelligence
Real-world time series are often governed by complex nonlinear dynamics. Understanding these underlying dynamics is crucial for precise future prediction. While deep learning has achieved major success in time series forecasting, many existing approaches do not explicitly model the dynamics. To bridge this gap, we introduce DeepEDM, a framework that integrates nonlinear dynamical systems modeling with deep neural networks. Inspired by empirical dynamic modeling (EDM) and rooted in Takens' theorem, DeepEDM presents a novel deep model that learns a latent space from time-delayed embeddings, and employs kernel regression to approximate the underlying dynamics, while leveraging efficient implementation of softmax attention and allowing for accurate prediction of future time steps. To evaluate our method, we conduct comprehensive experiments on synthetic data of nonlinear dynamical systems as well as real-world time series across domains. Our results show that DeepEDM is robust to input noise, and outperforms state-of-the-art methods in forecasting accuracy. Our code is available at: https://abrarmajeedi.github.io/deep_edm.
title LETS Forecast: Learning Embedology for Time Series Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.06454