Uncertainty and Explainability in Deep Rough Volatility: A Neural Information-Theoretic Posterior Approach

2026-09-25

AI Summary

This study addresses the neglect of parameter uncertainty and limited interpretability in calibrating rough volatility models by proposing a simulation-based inference framework. Methodologically, neural ratio estimation is employed to learn the posterior distribution of the rough Heston (rHeston) model, which is combined with heteroscedastic neural network surrogate pricing to generate exotic option price intervals that incorporate uncertainty. Furthermore, an information-theoretic interpretability approach termed Hellinger-SHAP is introduced to quantify prior-to-posterior information contraction, thereby identifying critical parameter regions. Experimental results demonstrate that the proposed method achieves robust coverage across various exotic options within posterior predictive intervals, significantly enhancing both the reliability and transparency of derivative pricing.

Abstract

Deep learning has substantially accelerated the calibration of complex stochastic-volatility models, but neural point calibration alone does not capture the uncertainty remaining after an implied-volatility (IV) surface has been observed. We develop a simulation-based inference framework for rough Heston (rHeston) calibration that learns the posterior distribution of the model parameters conditional on an IV surface. Using neural ratio estimation, we obtain calibrated posterior samples that can be propagated through heteroscedastic neural surrogate pricers for path-dependent exotic options. The resulting posterior-predictive distributions combine residual parameter uncertainty with conditional surrogate uncertainty and yield uncertainty-aware price intervals. We further introduce Hellinger-SHAP, an information-theoretic explainability method for posterior inference. Rather than attributing a single parameter point estimate, it applies local-background Kernel SHAP to a posterior-information functional measuring contraction from the prior to the posterior. This identifies maturity--moneyness regions associated with posterior information gain for individual rHeston parameters. In a simulation study, posterior-predictive intervals provide calibrated or conservative coverage across forward-start, barrier, and realized-variance claims, while point plug-in prices can be materially unreliable for selected contract regimes. Together, the UQ and XAI analyses provide a transparent framework for uncertainty-aware neural calibration and downstream exotic pricing under the specified prior-predictive model.

Problem

• rough volatility
• uncertainty quantification
• explainability
• model calibration
• exotic option pricing

Innovation

• Simulation-based inference
• Neural ratio estimation
• Rough Heston model
• Hellinger-SHAP
• Uncertainty quantification