Metraipolis › archive › dc_ff37a968709d

Regime-Gated Residual Mixture-of-Experts for Cross-Sectional Volatility Forecasting — arXiv:2608.12251

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12251
License (as archived)
CC0-1.0
Archived
2026-10-19T05:40:33.381Z
SHA-256 of the archived text
8ba894710c1dad1dc633ad7ac27fe0989ed254c52854bb4deb6ca804e52c6f23
Stable URL of this page
https://metraipolis.com/documento/dc_ff37a968709d

How to cite

Regime-Gated Residual Mixture-of-Experts for Cross-Sectional Volatility Forecasting — arXiv:2608.12251 — arXiv (en), https://arxiv.org/abs/2608.12251 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff37a968709d (Metraipolis archive dc_ff37a968709d, sha256 8ba894710c1dad1dc633ad7ac27fe0989ed254c52854bb4deb6ca804e52c6f23)
BibTeX
@misc{dcff37a968709d,
  title = {Regime-Gated Residual Mixture-of-Experts for Cross-Sectional Volatility Forecasting — arXiv:2608.12251},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12251},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff37a968709d; sha256 8ba894710c1dad1dc633ad7ac27fe0989ed254c52854bb4deb6ca804e52c6f23},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12251. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.LG).
Categorie arXiv: Statistical Finance (q-fin.ST) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.12251 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:18:32.559Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).