标签地平线悖论：金融预测中监督目标的再思考
The Label Horizon Paradox: Rethinking Supervision Targets in Financial Forecasting
AI总结：
本文提出标签地平线悖论，指出最优监督信号常偏离预测目标，并基于动态信噪比权衡理论，提出双层优化框架自动寻找最优代理标签，在金融数据集上取得一致改进。
摘要：
虽然深度学习通过复杂的架构革新了金融预测，但监督信号本身的设计却很少受到审视。我们挑战了训练标签必须严格反映推理目标的经典假设，揭示了标签地平线悖论：最优监督信号往往偏离预测目标，而是在由市场动态决定的中间地平线上转移。我们从理论上将这一现象归结为动态信噪比权衡，证明泛化取决于边际信号实现与噪声积累之间的竞争。为了将这一见解付诸实践，我们提出了一个双层优化框架，能够在单次训练运行中自主识别最优代理标签。在大型金融数据集上的大量实验表明，该方法相比传统基线取得了一致的改进，从而为金融预测中基于标签的研究开辟了新途径。
英文摘要：
While deep learning has revolutionized financial forecasting through sophisticated architectures, the design of the supervision signal itself is rarely scrutinized. We challenge the canonical assumption that training labels must strictly mirror inference targets, uncovering the Label Horizon Paradox: the optimal supervision signal often deviates from the prediction goal, shifting across intermediate horizons governed by market dynamics. We theoretically ground this phenomenon in a dynamic signal-noise trade-off, demonstrating that generalization hinges on the competition between marginal signal realization and noise accumulation. To operationalize this insight, we propose a bi-level optimization framework that autonomously identifies the optimal proxy label within a single training run. Extensive experiments on large-scale financial datasets demonstrate consistent improvements over conventional baselines, thereby opening new avenues for label-centric research in financial forecasting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
