训练后添加修正项，让时间序列预测模型精度提升30%。
Post-Training Corrections for Improved Time-Series Forecasting
- 训练完模型后，逐次应用精心选择的修正项提升预测。
- 在多个数据集上实现最高30%的准确率提升，开销极小。
- 适合已有模型但想进一步优化的工程师和研究人员。
时间序列预测在诸多商业领域至关重要，但依然极具挑战性。通常大型预测模型需一次性完成耗时耗资源的训练。训练结束后，一个自然的问题是：模型性能是否仍有提升空间？受提升技术启发，我们提出“训练后修正”概念，通过依次施加精心挑选的修正项来改进已训练模型的预测结果。该方法轻量、不依赖模型结构且可扩展，适用于实际场景。我们从仿射修正情形出发建立理论基础，并分析更一般设置下的预期性能增益与计算成本。在多个基准数据集上，该方法始终实现相比现有最先进模型最高达30%的预测准确率提升，且计算开销极低。
原文摘要 · Abstract (English)
Time-series forecasting is a critical task in various business domains, but it remains inherently challenging. Typically, large forecasting models are trained in a single, resource-intensive run. Once training is completed, a natural question arises:~\emph{is there still potential for meaningful improvement in the model's performance?} Motivated by techniques from boosting, we introduce the concept of~\emph{post-training corrections}. This approach enhances a trained forecaster by sequentially applying a carefully selected set of corrections to its predictions. Our method offers a lightweight, model-agnostic, and scalable strategy to improve forecasting performance in practical settings. We provide theoretical foundations for the approach, starting with the affine correction case, and analyze the expected performance gains and computational costs in more general settings. Across a range of benchmark datasets, our method consistently delivers up to a $30\%$ improvement in forecasting accuracy over existing state-of-the-art models, with minimal computational overhead.
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。