A generative adversarial network approach to calibration of local stochastic volatility models

Abstract

We propose a fully data-driven approach to calibrate local stochastic volatility (LSV) models, circumventing in particular the ad hoc interpolation of the volatility surface. To achieve this, we parametrize the leverage function by a family of feed-forward neural networks and learn their parameters directly from the available market option prices. This should be seen in the context of neural SDEs and (causal) generative adversarial networks: we generate volatility surfaces by specific neural SDEs, whose quality is assessed by quantifying, possibly in an adversarial manner, distances to market prices. The minimization of the calibration functional relies strongly on a variance reduction technique based on hedging and deep hedging, which is interesting in its own right: it allows the calculation of model prices and model implied volatilities in an accurate way using only small sets of sample paths. For numerical illustration we implement a SABR-type LSV model and conduct a thorough statistical performance analysis on many samples of implied volatility smiles, showing the accuracy and stability of the method.

arXiv commentReplacement for previous version: Major update of previous version to match the content of the published version

References in corpus (5)

• Pricing options and computing implied volatilities using neural networks
• Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis
• A neural network-based framework for financial model calibration
• Hedged Monte-Carlo: low variance derivative pricing with objective probabilities
• A* Tree Search for Portfolio Management

Cited by in corpus (6)

• Neural Controlled Differential Equations for Irregular Time Series
• The Universal Approximation Property
• The Signature Kernel is the solution of a Goursat PDE
• Conditional Sig-Wasserstein GANs for Time Series Generation
• Calibration of Local-Stochastic Volatility Models by Optimal Transport
• Consistent Recalibration Models and Deep Calibration