mlsanityData to 14 Oct 2026

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

arXiv 2608.12251 ↗First posted 12 Aug 2026q-fin.ST cs.LGcited by 0

On the map: Mixture-of-experts → MoE for time series and graphs

Abstract (arXiv)

Financial volatility is regime dependent, yet incorporating regime information into neural networks can also destabilize training. This paper asks where such information should enter a neural cross-sectional volatility forecasting model. We study five-day realized-volatility forecasts for 1,027 U.S. equities using a rolling walk-forward evaluation framework in which information, model capacity, hyperparameter tuning, and random seeds are matched across architectures. We propose 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. The base predictor models volatility from stock features, while a gating network uses regime state variables to route residual corrections. RG-ResMoE consistently outperforms a capacity-matched MLP in both forecasting accuracy and training stability in the main U.S. study. Similar gains are observed on an independent Japanese panel. The integration pathway is decisive: appending the same regime variables directly to the forecasting input degrades both predictive performance and training stability, whereas restricting them to the routing gate improves accuracy and Value-at-Risk calibration. Hard routing consistently underperforms soft routing. The results suggest that, in compact neural volatility forecasting models, the primary value of mixture-of-experts models lies less in increasing model capacity than in controlling how nonstationary regime information influences prediction.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts. Builds on 7 of its 23 references that are in the map. First posted on arXiv 12 Aug 2026.

Builds on

7 of 23 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts14 Oct
  2. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts24 Sep

Other references · 5

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  4. 2023From Sparse to Soft Mixtures of Expertscited by 248
  5. 2019Fixup Initialization: Residual Learning Without Normalizationcited by 198

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting
  2. 2024A Dynamic Approach to Stock Price Prediction: Comparing RNN and Mixture of Experts Models Across Different Volatility Profiles
  3. 2026HAN-Mamba: Hierarchical Selective State Space Networks for Multi-Scale Financial Volatility Forecasting
  4. 2026DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift
  5. 2026Integrating Inductive Biases in Transformers via Distillation for Financial Time Series Forecasting
  6. 2026Adaptive Financial Transformer with Regime-Gated Attention for Stock Return Prediction
  7. 2026Calibration Bets on the Past: Post-Training Quantization for Financial Time-Series Forecasting
  8. 2026Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control