Conditionally Identifiable Latent Representation for Multivariate Time Series with Structural Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chang, Minkey, Kim, Jae-Young
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918406221987840
author Chang, Minkey
Kim, Jae-Young
author_facet Chang, Minkey
Kim, Jae-Young
contents We propose the Identifiable Variational Dynamic Factor Model (iVDFM), which learns latent factors from multivariate time series with identifiability guarantees. By applying iVAE-style conditioning to the innovation process driving the dynamics rather than to the latent states, we show that factors are identifiable up to permutation and component-wise affine (or monotone invertible) transformations. Linear diagonal dynamics preserve this identifiability and admit scalable computation via companion-matrix and Krylov methods. We demonstrate improved factor recovery on synthetic data, stable intervention accuracy on synthetic SCMs, and competitive probabilistic forecasting on real-world benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22886
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Conditionally Identifiable Latent Representation for Multivariate Time Series with Structural Dynamics
Chang, Minkey
Kim, Jae-Young
Machine Learning
General Finance
Statistical Finance
We propose the Identifiable Variational Dynamic Factor Model (iVDFM), which learns latent factors from multivariate time series with identifiability guarantees. By applying iVAE-style conditioning to the innovation process driving the dynamics rather than to the latent states, we show that factors are identifiable up to permutation and component-wise affine (or monotone invertible) transformations. Linear diagonal dynamics preserve this identifiability and admit scalable computation via companion-matrix and Krylov methods. We demonstrate improved factor recovery on synthetic data, stable intervention accuracy on synthetic SCMs, and competitive probabilistic forecasting on real-world benchmarks.
title Conditionally Identifiable Latent Representation for Multivariate Time Series with Structural Dynamics
topic Machine Learning
General Finance
Statistical Finance
url https://arxiv.org/abs/2603.22886