Gargi Vijay Borde

Regime-Gated Residual Mixture-of-Experts for Cross-Sectional Volatility Forecasting

This paper proposes RG-ResMoE, a regime-gated residual mixture-of-experts architecture in which regime information is used only for expert routing rather than for direct forecasting, which consistently outperforms a capacity-matched MLP in both forecasting accuracy and training stability in the main U.S. study.