Saved in:
Bibliographic Details
Main Authors: Koyuncu, Batuhan, DeVries, Rachael, Winther, Ole, Valera, Isabel
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.01544
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912409468272640
author Koyuncu, Batuhan
DeVries, Rachael
Winther, Ole
Valera, Isabel
author_facet Koyuncu, Batuhan
DeVries, Rachael
Winther, Ole
Valera, Isabel
contents We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient individualized imputation and forecasting. By integrating implicit neural representations with latent variable models, TV-INRs learn distributions over time-continuous generator functions conditioned on signal-specific covariates. Unlike existing approaches that require extensive training, fine-tuning or meta-learning, our method achieves accurate individualized predictions through a single forward pass. Our experiments demonstrate that with a single TV-INRs instance, we can accurately solve diverse imputation and forecasting tasks, offering a computationally efficient and scalable solution for real-world applications. TV-INRs excel especially in low-data regimes, where it outperforms existing methods by an order of magnitude in mean squared error for imputation task.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01544
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Temporal Variational Implicit Neural Representations
Koyuncu, Batuhan
DeVries, Rachael
Winther, Ole
Valera, Isabel
Machine Learning
We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient individualized imputation and forecasting. By integrating implicit neural representations with latent variable models, TV-INRs learn distributions over time-continuous generator functions conditioned on signal-specific covariates. Unlike existing approaches that require extensive training, fine-tuning or meta-learning, our method achieves accurate individualized predictions through a single forward pass. Our experiments demonstrate that with a single TV-INRs instance, we can accurately solve diverse imputation and forecasting tasks, offering a computationally efficient and scalable solution for real-world applications. TV-INRs excel especially in low-data regimes, where it outperforms existing methods by an order of magnitude in mean squared error for imputation task.
title Temporal Variational Implicit Neural Representations
topic Machine Learning
url https://arxiv.org/abs/2506.01544