用生成模型优化金融时间序列预测，提升准确率。
RefineBridge: Generative Bridge Models Improve Financial Forecasting by Foundation Models
- 基于薛定谔桥框架构建可学习的修正模块，迭代改进预测结果。
- 在多个金融基准上，显著提升主流时序模型的预测性能。
- 适合需要高精度金融预测的量化研究与实际应用者。
金融时间序列预测对基于Transformer的时序基础模型（TSFMs）极具挑战，因数据存在非平稳性、重尾分布及高频噪声。低秩适配（LoRA）虽是参数高效微调的流行方法，但在金融数据上仍表现不足，因其保留了原始模型结构与训练目标，未能有效补充基础模型。为此，本文提出新型精炼模块RefineBridge，基于可计算的薛定谔桥（Schrödinger Bridge, SB）生成框架，以TSFM的预测为生成先验，真实观测值为目标，学习上下文相关的随机传输映射，迭代逼近真实目标，从低质量先验逐步优化预测。在多个金融基准上的模拟实验表明，RefineBridge在不同预测时长下均持续提升最先进TSFMs的性能。
原文摘要 · Abstract (English)
Financial time series forecasting is particularly challenging for transformer-based time series foundation models (TSFMs) due to non-stationarity, heavy-tailed distributions, and high-frequency noise present in data. Low-rank adaptation (LoRA) has become a popular parameter-efficient method for adapting pre-trained TSFMs to downstream data domains. However, it still underperforms in financial data, as it preserves the network architecture and training objective of TSFMs rather than complementing the foundation model. To further enhance TSFMs, we propose a novel refinement module, RefineBridge, built upon a tractable Schrödinger Bridge (SB) generative framework. Given the forecasts of TSFM as generative prior and the observed ground truths as targets, RefineBridge learns context-conditioned stochastic transport maps to improve TSFM predictions, iteratively approaching the ground-truth target from even a low-quality prior. Simulations on multiple financial benchmarks demonstrate that RefineBridge consistently improves the performance of state-of-the-art TSFMs across different prediction horizons.
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。