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.

翻译：尽管深度学习通过复杂架构彻底改变了金融预测，但监督信号本身的设计却鲜少受到审视。我们挑战了训练标签必须严格反映推理目标的经典假设，揭示了标签视界悖论：最优监督信号往往偏离预测目标，并在市场动态主导的中间视界间发生偏移。我们将这一现象理论化为动态信噪权衡，证明泛化性能取决于边际信号实现与噪声累积之间的竞争。为实践这一洞见，我们提出了一个双层优化框架，能在单次训练运行中自主识别最优代理标签。在大规模金融数据集上的广泛实验表明，该方法相较传统基线模型取得了持续改进，从而为金融预测中以标签为中心的研究开辟了新途径。