aiqbench analysis
This paper introduces CircuITS, a probabilistic architecture leveraging sum-product networks to solve the specific challenge of forecasting irregular multivariate time series with consistent uncertainty quantification. By structurally guaranteeing valid joint distributions, the model addresses critical limitations in existing methods regarding marginalization and expressivity for complex temporal dependencies. The approach represents a significant methodological advance in probabilistic machine learning for handling non-uniformly sampled sensor data.
Probabilistic Circuits for Irregular Multivariate Time Series Forecasting
arXiv:2604.27814v3 Announce Type: replace Abstract: Joint probabilistic modeling is essential for forecasting irregular multivariate time series (IMTS) to accurately quantify uncertainty. Existing approaches often struggle to balance model expressivity with consistent marginalization, frequently leading to unreliable or contradictory forecasts. To address this, we propose CircuITS, a novel architecture for probabilistic IMTS forecasting based on sum-product networks (SPNs). Our model is flexible in capturing intricate dependencies between time series channels while structurally guaranteeing valid joint distributions. Experiments on five real-world datasets demonstrate that CircuITS achieves superior joint and marginal density estimation compared to state-of-the-art baselines.
Abstract:Joint probabilistic modeling is essential for forecasting irregular multivariate time series (IMTS) to accurately quantify uncertainty. Existing approaches often struggle to balance model expressivity with consistent marginalization, frequently leading to unreliable or contradictory forecasts. To address this, we propose CircuITS, a novel architecture for probabilistic IMTS forecasting based on sum-product networks (SPNs). Our model is flexible in capturing intricate dependencies between time series channels while structurally guaranteeing valid joint distributions. Experiments on five real-world datasets demonstrate that CircuITS achieves superior joint and marginal density estimation compared to state-of-the-art baselines.
Machine Learning (cs.LG)
arXiv:2604.27814 [cs.LG]
(or arXiv:2604.27814v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2604.27814 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 181 words
Related coverage
FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation
arXiv · Sep 5, 2026
Gaussian Mixture Copula Processes for Irregular Time Series
arXiv · Sep 30, 2026
TimesFM-3: A zero-shot foundation model for multivariate forecasting
Google Research · Aug 31, 2026
QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting
arXiv · Oct 7, 2026