Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kayaalp, Mert, Turkmen, Caner, Shchur, Oleksandr, Mercado, Pedro, Ansari, Abdul Fatir, Bohlke-Schneider, Michael, Wang, Bernie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910019567484928
author Kayaalp, Mert
Turkmen, Caner
Shchur, Oleksandr
Mercado, Pedro
Ansari, Abdul Fatir
Bohlke-Schneider, Michael
Wang, Bernie
author_facet Kayaalp, Mert
Turkmen, Caner
Shchur, Oleksandr
Mercado, Pedro
Ansari, Abdul Fatir
Bohlke-Schneider, Michael
Wang, Bernie
contents Is bigger always better for time series foundation models? With the question in mind, we explore an alternative to training a single, large monolithic model: building a portfolio of smaller, pretrained forecasting models. By applying ensembling or model selection over these portfolios, we achieve competitive performance on large-scale benchmarks using much fewer parameters. We explore strategies for designing such portfolios and find that collections of specialist models consistently outperform portfolios of independently trained generalists. Remarkably, we demonstrate that post-training a base model is a compute-effective approach for creating sufficiently diverse specialists, and provide evidences that ensembling and model selection are more compute-efficient than test-time fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06419
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting
Kayaalp, Mert
Turkmen, Caner
Shchur, Oleksandr
Mercado, Pedro
Ansari, Abdul Fatir
Bohlke-Schneider, Michael
Wang, Bernie
Machine Learning
Is bigger always better for time series foundation models? With the question in mind, we explore an alternative to training a single, large monolithic model: building a portfolio of smaller, pretrained forecasting models. By applying ensembling or model selection over these portfolios, we achieve competitive performance on large-scale benchmarks using much fewer parameters. We explore strategies for designing such portfolios and find that collections of specialist models consistently outperform portfolios of independently trained generalists. Remarkably, we demonstrate that post-training a base model is a compute-effective approach for creating sufficiently diverse specialists, and provide evidences that ensembling and model selection are more compute-efficient than test-time fine-tuning.
title Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2510.06419