Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models

DOI10.1080/14697688.2020.1817974zbMath1479.91400OpenAlexW3095372661MaRDI QIDQ5014167

Blanka Horvath, Aitor Muguruza, Mehdi Tomas

Publication date: 1 December 2021

Published in: Quantitative Finance (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/14697688.2020.1817974

zbMATH Keywords

Monte Carlocalibrationmachine learningmodel assessmentVolterra processrough volatilityvolatility modellingaccurate price approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Derivative securities (option pricing, hedging, etc.) (91G20)

Related Items (18)

Empirical analysis of rough and classical stochastic volatility models to the SPX and VIX markets ⋮ Calibration to FX triangles of the 4/2 model under the benchmark approach ⋮ Deep calibration of financial models: turning theory into practice ⋮ Deep differentiable reinforcement learning and optimal trading ⋮ An unsupervised deep learning approach to solving partial integro-differential equations ⋮ Unbiased Deep Solvers for Linear Parametric PDEs ⋮ Derivatives of feed-forward neural networks and their application in real-time market risk management ⋮ Arbitrage-Free Implied Volatility Surface Generation with Variational Autoencoders ⋮ Robustness and sensitivity analyses of rough Volterra stochastic volatility models ⋮ Boundary-safe PINNs extension: application to non-linear parabolic PDEs in counterparty credit risk ⋮ A two-step framework for arbitrage-free prediction of the implied volatility surface ⋮ SABR equipped with AI wings ⋮ A generative model of a limit order book using recurrent neural networks ⋮ Applications of artificial neural networks to simulating Lévy processes ⋮ Reinforcement learning with dynamic convex risk measures ⋮ Applications of fractional gradient descent method with adaptive momentum in BP neural networks ⋮ From microscopic price dynamics to multidimensional rough volatility models ⋮ Deep ReLU neural networks overcome the curse of dimensionality for partial integrodifferential equations

Uses Software

• L-BFGS-B
• MultiMin
• DFVLR-SQP

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Asymptotic analysis for stochastic volatility: martingale expansion
• On the probability of hitting the boundary for Brownian motions on the SABR plane
• Approximation and estimation bounds for artificial neural networks
• Differential evolution -- a simple and efficient heuristic for global optimization over continuous spaces
• Perfect hedging in rough Heston models
• Multilayer feedforward networks are universal approximators
• Provable approximation properties for deep neural networks
• Approximation properties of a multilayered feedforward artificial neural network
• Derivative-free optimization: a review of algorithms and comparison of software implementations
• On the short-time behavior of the implied volatility for jump-diffusion models with stochastic volatility
• Arbitrage-free SVI volatility surfaces
• An Algorithm for Least-Squares Estimation of Nonlinear Parameters
• Algorithm 778: L-BFGS-B
• On VIX futures in the rough Bergomi model
• Volatility is rough
• On an efficient multiple time step Monte Carlo simulation of the SABR model
• Probability Distribution in the SABR Model of Stochastic Volatility
• Dirichlet Forms and Finite Element Methods for the SABR Model
• Pathwise large deviations for the rough Bergomi model
• Machine learning for quantitative finance: fast derivative pricing, hedging and fitting
• Mass at zero in the uncorrelated SABR model and implied volatility asymptotics
• Pricing under rough volatility
• Asymptotic behaviour of randomised fractional volatility models
• Short-time near-the-money skew in rough fractional volatility models
• Deep hedging
• Quelques applications de la formule de changement de variables pour les semimartingales
• A Simplex Method for Function Minimization
• The characteristic function of rough Heston models
• A method for the solution of certain non-linear problems in least squares
• A regularity structure for rough volatility
• Hybrid scheme for Brownian semistationary processes

This page was built for publication: Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models