论文概要
研究领域: ML 作者: Aliaksei Kaliutau 发布时间: 2026-07-24 arXiv: 2607.22491
中文摘要
波动率预测由持久性和测量噪声主导，为非线性模型留下的残差结构有限。本文引入易感架构(SUSA)，一种用于波动率预测的储层设计原则，及其两个具体实现，基于复值开链和周期性储层以及体制条件化专家来解释平静、 onset、恢复和持续压力状态下的储层特征。本文还在Qiskit中实现了开放系统
-量子比特对应物，同时保留共同的AR-Ridge锚点和在QLIKE下训练的有限残差校正。本文使用三个不相交的时间顺序训练、验证和测试折，在16个美国股票和交易所交易基金序列上评估模型，输入窗口为12个观测值，预测范围为5个观测值。所提出的模型与GARCH竞争性地执行，对特定资产(IWM, XLP)实现了统计显著的QLIKE改进。此外，模型的预测补充了HARQ式预测：堆叠集成在最强的单个模型上平均改进了0.0116的QLIKE，并在75%的测试场景中获胜。
原文摘要
Volatility forecasting is dominated by persistence and measurement noise, leaving limited residual structure for nonlinear models to exploit. We introduce Susceptible Architectures (SUSA), a reservoir-design principle for volatility forecasting, and its two concrete implementations, based on complex-valued open-chain and periodic reservoirs and regime-conditioned experts to interpret reservoir features across calm, onset, recovery, and persistent-stress states. We also implement open-system -qubit counterparts in Qiskit while retaining a common AR-Ridge anchor and a bounded residual correction trained under QLIKE. We evaluate models on 16 U.S. equity and exchange-traded-fund series using three disjoint chronological training, validation, and test folds, a 12-observation input window, an…
— 自动采集于 2026-07-28
#论文 #arXiv #ML #小凯