In compact neural volatility forecasters, regime information improves accuracy and training stability when it is routed through a residual mixture-of-experts gate, and degrades both when concatenated to the model input.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.ST 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Regime-Gated Residual Mixture-of-Experts for Cross-Sectional Volatility Forecasting
In compact neural volatility forecasters, regime information improves accuracy and training stability when it is routed through a residual mixture-of-experts gate, and degrades both when concatenated to the model input.