激进杠杆下神经网络驱动的波动率拖累缓解
Neural Network-Driven Volatility Drag Mitigation under Aggressive Leverage
- Université Paris-Saclay, CentraleSupélec（巴黎萨克雷大学、中央高等电力学院）
- Dipartimento di Fisica e Astronomia “Ettore Majorana” Catania（卡塔尼亚大学埃托雷·马约拉纳物理与天文系）
- Dipartimento di Fisica e Chimica Palermo（巴勒莫大学物理与化学系）
- Complexity Science Hub Vienna（维也纳复杂科学中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究针对全局最小方差投资组合优化，提出模块化端到端神经网络的紧凑重构，通过特定参数替换和模块简化大幅减少可学习参数，经样本外测试和交易模拟器验证，能在不损回报下降低方差，提升杠杆弹性与资本效率。
AI中文摘要：
本文介绍了一种用于全局最小方差投资组合优化的模块化端到端神经网络的紧凑重构，它将模型复杂性与回溯窗口长度和投资范围大小解耦。用一个五参数双曲加权移动平均线与饱和指数相结合取代原来的2400参数滞后变换层，双向门控循环单元特征清理模块和简化的边际波动率网络将可学习参数总数从39586减少到仅2175。在针对最先进的非线性收缩和风险平价基准的样本外测试中，紧凑网络在不影响预期回报的情况下实现了最低的实际投资组合方差。在长期约束下，方差降低支持更高的杠杆率，同时保持可比的回撤控制。在包含实际追加保证金动态的高保真交易模拟器中的验证证实了增强的过度杠杆弹性。这些发现表明，端到端方差最小化架构可以在不牺牲风险调整后性能的情况下实现显著的参数效率和强大的资本效率提升。
英文摘要：
This paper introduces a compact reformulation of a modular end-to-end neural network for global minimum-variance portfolio optimization that decouples model complexity from both look-back window length and universe size. A five-parameter hyperbolic weighted moving average combined with a saturating exponential replaces the original 2,400-parameter lag-transformation layer, and a bidirectional gated-recurrent-unit eigencleaning module together with a streamlined marginal-volatility network reduce total learnable parameters from 39,586 to just 2,175. In out-of-sample tests against state-of-the-art nonlinear-shrinkage and risk-parity benchmarks, the compact network attains the lowest realized portfolio variance without compromising expected return. Under long-only constraints, the variance reduction supports substantially higher leverage while maintaining comparable drawdown control. Validation in a high-fidelity trading simulator that incorporates realistic margin-call dynamics confirms enhanced over-leverage resilience. These findings demonstrate that end-to-end variance-minimization architectures can achieve substantial parameter efficiency and robust capital-efficiency gains without sacrificing risk-adjusted performance.
