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

by   Christa Cuchiero, et al.

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, 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 to calculate 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 analyis on many samples of implied volatility smiles, showing the accuracy and stability of the method.


page 1

page 2

page 3

page 4


Unbiasing and robustifying implied volatility calibration in a cryptocurrency market with large bid-ask spreads and missing quotes

We design a novel calibration procedure that is designed to handle the s...

Beyond Surrogate Modeling: Learning the Local Volatility Via Shape Constraints

We explore the abilities of two machine learning approaches for no-arbit...

Gated deep neural networks for implied volatility surfaces

In this paper, we propose a gated deep neural network model to predict i...

FuNVol: A Multi-Asset Implied Volatility Market Simulator using Functional Principal Components and Neural SDEs

This paper introduces a new approach for generating sequences of implied...

Robust pricing and hedging via neural SDEs

Mathematical modelling is ubiquitous in the financial industry and drive...

Applying Deep Learning to Calibrate Stochastic Volatility Models

Stochastic volatility models, where the volatility is a stochastic proce...

A threshold model for local volatility: evidence of leverage and mean reversion effects on historical data

In financial markets, low prices are generally associated with high vola...

Please sign up or login with your details

Forgot password? Click here to reset