Saved in:
Bibliographic Details
Main Authors: Yang, Yang, Yin, Du, Xue, Hao, Salim, Flora
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.10364
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914566888226816
author Yang, Yang
Yin, Du
Xue, Hao
Salim, Flora
author_facet Yang, Yang
Yin, Du
Xue, Hao
Salim, Flora
contents Modeling uncertainty in heavy-tailed time series remains a critical challenge for deep probabilistic forecasting models, which often struggle to capture abrupt, extreme events. While Lévy stable distributions offer a natural framework for modeling such non-Gaussian behaviors, the intractability of their probability density functions severely limits conventional likelihood-based inference. To address this, we introduce DeepLévy, a neural framework that learns mixtures of Lévy stable distributions by minimizing the discrepancy between empirical and parametric characteristic functions. DeepLévy incorporates a mixture mechanism that adaptively learns context-dependent weights and parameters over multiple Lévy components, enabling flexible multi-horizon uncertainty modeling. Evaluations on both real and synthetic datasets demonstrate that DeepLévy outperforms state-of-the-art deep probabilistic forecasting approaches in tail risk metrics, especially under extreme volatility.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10364
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DeepLévy: Learning Heavy-Tailed Uncertainty in Highly Volatile Time Series
Yang, Yang
Yin, Du
Xue, Hao
Salim, Flora
Machine Learning
Modeling uncertainty in heavy-tailed time series remains a critical challenge for deep probabilistic forecasting models, which often struggle to capture abrupt, extreme events. While Lévy stable distributions offer a natural framework for modeling such non-Gaussian behaviors, the intractability of their probability density functions severely limits conventional likelihood-based inference. To address this, we introduce DeepLévy, a neural framework that learns mixtures of Lévy stable distributions by minimizing the discrepancy between empirical and parametric characteristic functions. DeepLévy incorporates a mixture mechanism that adaptively learns context-dependent weights and parameters over multiple Lévy components, enabling flexible multi-horizon uncertainty modeling. Evaluations on both real and synthetic datasets demonstrate that DeepLévy outperforms state-of-the-art deep probabilistic forecasting approaches in tail risk metrics, especially under extreme volatility.
title DeepLévy: Learning Heavy-Tailed Uncertainty in Highly Volatile Time Series
topic Machine Learning
url https://arxiv.org/abs/2605.10364