用小模型组合替代大模型，高效预测时间序列。
Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting
- 构建多个预训练小模型组成的组合，替代单一大模型。
- 参数减少90%以上，性能仍达主流基准水平。
- 适合资源有限但需高精度预测的场景。
大规模时间序列基础模型是否越大越好？本文探索了一种替代方案：构建由多个小型预训练预测模型组成的小型组合。通过在测试时对这些模型进行集成或选择，仅使用极少参数即可在大规模基准上达到竞争性性能。研究发现，专家型模型组合始终优于独立训练的通用型模型组合。令人惊讶的是，对基础模型进行微调后可高效生成足够多样化的专家模型，且集成与模型选择比测试时微调更节省计算成本。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。