用不确定性控制生成过程,让金融预测更稳健可靠。
Uncertainty-Gated Generative Modeling
- 以不确定性为信号,动态调控模型表示、传播与生成。
- 在纽约电力市场数据上,均方误差降低63.5%,达0.1281。
- 适合对风险敏感的金融时序预测场景,抗冲击能力强。
金融时间序列预测是高风险问题,制度变迁和突发冲击常使过于自信的点预测模型带来严重后果。本文提出不确定性门控生成建模(UGGM),将不确定性作为内部控制信号,通过门控重参数化调节表示,通过相似性与置信度路由控制信息传播,并通过不确定性调控的预测分布实现生成,同时引入不确定性驱动的正则化与校准机制以缓解误校准问题。在弱创新自编码器(WIAE-GPF)基础上构建的UG-WIAE-GPF模型,在纽约独立系统运营商(NYISO)数据集上实现了63.5%的均方误差降低(从0.3508降至0.1281),并在冲击区间内表现更稳健(均方误差从0.2739降至0.1748)。
原文摘要 · Abstract (English)
Financial time-series forecasting is a high-stakes problem where regime shifts and shocks make point-accurate yet overconfident models dangerous. We propose Uncertainty-Gated Generative Modeling (UGGM), which treats uncertainty as an internal control signal that gates (i) representation via gated reparameterization, (ii) propagation via similarity and confidence routing, and (iii) generation via uncertainty-controlled predictive distributions, together with uncertainty-driven regularization and calibration to curb miscalibration. Instantiated on Weak Innovation AutoEncoder (WIAE-GPF), our UG-WIAE-GPF significantly improves risk-sensitive forecasting, delivering a 63.5\% MSE reduction on NYISO (0.3508 $\rightarrow$ 0.1281), with improved robustness under shock intervals (mSE: 0.2739 $\rightarrow$ 0.1748).
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。