首页 > AI前沿 > Interweaving Marginals into Multivariate Sample Paths: Training-Free Dependence Construction for Probabilistic Time Series Foundation Models

Interweaving Marginals into Multivariate Sample Paths: Training-Free Dependence Construction for Probabilistic Time Series Foundation Models

arXiv机器学习 2026-09-22 18:35 5 阅读 查看原文

Probabilistic time series foundation models (TSFMs) provide coordinate-wise predictive distributions, but these marginals do not determine a joint distribution over multivariate future trajectories.

We study training-free coupling of frozen TSFM marginals into multivariate forecast sample paths.

Our primary evaluation fixes the empirical marginal sample multiset at every channel--horizon coordinate across methods, isolating the effect of coupling alone.

Historical temporal and channel relations substantially improve their corresponding dependence diagnostics.

The same pattern persists when the fixed-marginal constraint is removed and paths are sampled directly, and remains present under native multivariate backbone inference.

These results support treating dependence reconstruction as a distinct post-processing problem for probabilistic TSFMs.