Learning CHARME models with neural networks
On the map: Mixture-of-experts → MoE for time series and graphs
Abstract (arXiv)
In this paper, we consider a model called CHARME (Conditional Heteroscedastic Autoregressive Mixture of Experts), a class of generalized mixture of nonlinear nonparametric AR-ARCH time series. Under certain Lipschitz-type conditions on the autoregressive and volatility functions, we prove that this model is stationary, ergodic and τ-weakly dependent. These conditions are much weaker than those presented in the literature that treats this model. Moreover, this result forms the theoretical basis for deriving an asymptotic theory of the underlying (non)parametric estimation, which we present for this model. As an application, from the universal approximation property of neural networks (NN), we develop a learning theory for the NN-based autoregressive functions of the model, where the strong consistency and asymptotic normality of the considered estimator of the NN weights and biases are guaranteed under weak conditions.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts. First posted on arXiv 8 Feb 2020.
Builds on
No reference list yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Regime-Gated Residual Mixture-of-Experts for Cross-Sectional Volatility Forecasting
- 2022Functional Mixtures-of-Experts
- 2024Low-dimensional approximations of the conditional law of Volterra processes: a non-positive curvature approach
- 2024A Dynamic Approach to Stock Price Prediction: Comparing RNN and Mixture of Experts Models Across Different Volatility Profiles
- 2023Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts
- 2026Voltic: Distinguishing Volatility from Stochasticity in Recurrent Memory
- 2026Learning Nonlinear Regime Transitions via Semi-Parametric State-Space Models
- 2021A non-asymptotic approach for model selection via penalization in high-dimensional mixture of experts models