Skip to content

SGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Models

Sep 2026 · arXiv.org · Vol abs/2609.28582 · 0 citations · 36 references
Computer Science Mathematics

TL;DR

The proposed SGA first characterizes the topology of all potential forecast branches using a directed acyclic graph, such that the graph complexity bounds the uncertainty of multi-step TSFM forecasts, and then precisely measures the graph complexity by integrating both topological information and TSFM-inherent stochasticity.

Abstract

The recent emergence of Time Series Foundation Models (TSFMs) has significantly advanced multi-step forecasting performance, enabling accurate predictions over extended future horizons. However, existing TSFMs often suffer from significantly inherent uncertainty, which typically manifests as derived forecast branches emerging at each time step and spreading to subsequent steps; different forecast branches often exhibit varying forecasting performance, thereby undermining the credibility of TSFM forecasts. In this paper, we propose the Slicing-Graphing-Alignment (SGA) method to quantify the uncertainty of multi-step TSFM forecasts. The proposed SGA first characterizes the topology of all potential forecast branches using a directed acyclic graph, such that the graph complexity bounds the uncertainty of multi-step forecasts, and then precisely measures the graph complexity by integrating both topological information and TSFM-inherent stochasticity. Experimental results conducted on 11 TSFMs and 27 datasets demonstrate that (i) SGA achieves the best performance when ranking predictive errors with uncertainty estimates; (ii) SGA works with a more extensive and more precise sampling coverage than those of existing UQ methods, deriving a quantification mechanism fundamentally different from those of established ones; and (iii) larger model scales of TSFMs correlate with lower uncertainty estimates of multi-step forecasts, suggesting another empirical scaling law for uncertainty quantification of multi-step TSFM forecasts.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

Chronos-2: A foundation model for multivariate time series forecasting

Chronos-2 is introduced, a foundation model for zero-shot forecasting that models the interactions between multivariate time series and heterogeneous covariates, which commonly arise in scientific applications and shows that a single pretrained model can capture structure shared across temporal systems.

Abdul Fatir Ansari, Oleksandr Shchur, Jaris Küken et al. · 0 citations
#machine learning Preprint Oct 2026

Benchmarking Time Series Foundation Models for Load Forecasting Under Covariate Uncertainty

Accurate short-term load forecasting (STLF) is essential for the reliable and efficient operation of modern power systems. While time series foundation models (TSFMs) have recently demonstrated remarkable performance across a wide range of forecasting tasks, their effectiveness for STLF under realistic operational cond...

Tomas Kaljevic, I. Arzola, Yu Zhang · 0 citations
Sep 2026

TSCNet: A Trend-Seasonality Coupled Network for Efficient Multivariate Time Series Forecasting.

A forecasting framework that explicitly models the coupling between trend and seasonality, and a heteroscedastic Laplace loss function that combines uncertainty weighting with heteroscedastic modeling, reducing the impact of error accumulation over long prediction horizons and enhancing robustness to outliers and heavy...

Zi-Qiong Li, He-Yu Chai, Xin-Ru Liu et al. · 0 citations
Conference Oct 2026

A Multi-Dimensional Benchmark of Large Language Models for Time Series Forecasting

Large Language Models (LLMs) have recently been applied to time series forecasting via prompt-based inference, yet their evaluation remains limited by potential benchmark contamination and an overemphasis on accuracy. We introduce a systematic benchmark that evaluates LLMs across accuracy, efficiency, cost, and environ...

Zairo Bastos, Fernanda Scarcela, Wesley Barbosa et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Explaining Time Series Forecasting with Horizon-Resolved Attribution

This paper proposes Horizon-Resolved eXplanation, which adds a horizon axis to the explanation, so that every forecast step receives its own importance map, and shows that this step-wise dependence is low-dimensional, as the explanations of all steps are built from a few shared maps whose number does not grow with the...

Seung-Han Lee, Jun Seo, Jaehoon Lee et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.