Deep PPDEs for Rough Local Stochastic Volatility

We introduce the notion of rough local stochastic volatility models, extending the classical concept to the case where volatility is driven by some Volterra process. In this setting, we show that the pricing function is the solution to a path-dependent PDE, for which we develop a numerical scheme based on Deep Learning techniques. Numerical simulations suggest that the latter is extremely efficient, and provides a good alternative to classical Monte Carlo simulations.

[1]  Antoine Jacquier,et al.  Asymptotic behaviour of randomised fractional volatility models , 2019, J. Appl. Probab..

[2]  J. Vives,et al.  On the Short-Time Behavior of the Implied Volatility for Jump-Diffusion Models With Stochastic Volatility , 2006 .

[3]  Mikko S. Pakkanen,et al.  Turbocharging Monte Carlo pricing for the rough Bergomi model , 2017, 1708.02563.

[4]  Jim Gatheral,et al.  Affine forward variance models , 2018, Finance and Stochastics.

[5]  M. Rosenbaum,et al.  Volatility is rough , 2014, 1410.3394.

[6]  Hai-ping Shi.  Backward stochastic differential equations in finance , 2010 .

[7]  L. Decreusefond,et al.  Stochastic Analysis of the Fractional Brownian Motion , 1999 .

[8]  Benjamin Jourdain,et al.  Existence of a calibrated regime switching local volatility model , 2016, Mathematical Finance.

[9]  M. Rosenbaum,et al.  Roughening Heston , 2019 .

[10]  Justin A. Sirignano,et al.  DGM: A deep learning algorithm for solving partial differential equations , 2017, J. Comput. Phys..

[11]  Paul Gassiat,et al.  On the martingale property in the rough Bergomi model , 2018, Electronic Communications in Probability.

[12]  G. Barles,et al.  Convergence of approximation schemes for fully nonlinear second order equations , 1990, 29th IEEE Conference on Decision and Control.

[13]  Dimitrios I. Fotiadis,et al.  Artificial neural networks for solving ordinary and partial differential equations , 1997, IEEE Trans. Neural Networks.

[14]  Henry Stone.  Calibrating rough volatility models: a convolutional neural network approach , 2018 .

[15]  B. Jourdain,et al.  Loss of martingality in asset price models with lognormal stochastic volatility , 2022 .

[16]  Alaeddin Malek,et al.  Numerical solution for high order differential equations using a hybrid neural network - Optimization method , 2006, Appl. Math. Comput..

[17]  Julien Guyon,et al.  Nonlinear Option Pricing , 2013 .

[18]  F. Black,et al.  The Pricing of Options and Corporate Liabilities , 1973, Journal of Political Economy.

[19]  Jean Picard,et al.  Representation formulae for the fractional Brownian motion , 2009, 0912.3168.

[20]  Raul Tempone,et al.  Hierarchical adaptive sparse grids and quasi-Monte Carlo for option pricing under the rough Bergomi model , 2018 .

[21]  Philipp Harms.  Strong convergence rates for Markovian representations of fractional Brownian motion , 2019, 1902.01471.

[22]  David Siska,et al.  Martingale Functional Control variates via Deep Learning , 2018, ArXiv.

[23]  Jim Gatheral.  The Volatility Surface: A Practitioner's Guide , 2006 .

[24]  I. Gyöngy.  Mimicking the one-dimensional marginal distributions of processes having an ito differential , 1986 .

[25]  Frederi Viens,et al.  A martingale approach for fractional Brownian motions and related path dependent PDEs , 2017, The Annals of Applied Probability.

[26]  Bruno Dupire.  Pricing with a Smile , 1994 .

[27]  Mikko S. Pakkanen,et al.  Hybrid scheme for Brownian semistationary processes , 2015, Finance Stochastics.

[28]  Blanka Horvath,et al.  Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models , 2019, Quantitative Finance.

[29]  Zhenjie Ren,et al.  On the convergence of monotone schemes for path-dependent PDE , 2015, 1504.01872.

[30]  Alan L. Lewis.  A Simple Option Formula for General Jump-Diffusion and Other Exponential Levy Processes , 2001 .

[31]  Hongzhong Zhang,et al.  Asymptotics for Rough Stochastic Volatility Models , 2017, SIAM J. Financial Math..

[32]  N. Touzi,et al.  Viscosity solutions of fully nonlinear parabolic path dependent PDEs: Part II , 2012, 1210.0007.

[33]  F. Comte,et al.  Long memory continuous time models , 1996 .

[34]  Jim Gatheral,et al.  Rational Approximation of the Rough Heston Solution , 2019 .

[35]  Xavier Warin,et al.  Machine Learning for Semi Linear PDEs , 2018, Journal of Scientific Computing.

[36]  Jim Gatheral,et al.  Pricing under rough volatility , 2015 .

[37]  Patrick Roome,et al.  Asymptotic Behaviour of the Fractional Heston Model , 2014 .

[38]  Jim Gatheral,et al.  Arbitrage-free SVI volatility surfaces , 2012, 1204.0646.

[39]  Paul Gassiat,et al.  A regularity structure for rough volatility , 2017, Mathematical Finance.

[40]  Huyên Pham,et al.  Some machine learning schemes for high-dimensional nonlinear PDEs , 2019, ArXiv.

[41]  Arnulf Jentzen,et al.  Solving high-dimensional partial differential equations using deep learning , 2017, Proceedings of the National Academy of Sciences.

[42]  B. Mandelbrot,et al.  Fractional Brownian Motions, Fractional Noises and Applications , 1968 .

[43]  Chiheb Ben Hammouda,et al.  Hierarchical adaptive sparse grids for option pricing under the rough Bergomi model , 2018, 1812.08533.

[44]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[45]  M. Rosenbaum,et al.  The characteristic function of rough Heston models , 2016, 1609.02108.

[46]  G. Barles,et al.  Convergence of approximation schemes for fully nonlinear second order equations , 1991 .

[47]  N. Touzi,et al.  An overview of Viscosity Solutions of Path-Dependent PDEs , 2014, 1408.5267.

[48]  Nizar Touzi,et al.  Viscosity solutions of fully nonlinear parabolic path dependent PDEs: Part I , 2016 .

[49]  P. Tankov,et al.  Volatility Options in Rough Volatility Models , 2018, 1802.01641.

[50]  Antoine Jacquier,et al.  Pathwise large deviations for the rough Bergomi model , 2017, Journal of Applied Probability.

[51]  Mathieu Rosenbaum,et al.  The microstructural foundations of leverage effect and rough volatility , 2018, Finance Stochastics.

[52]  Gilles Pagès,et al.  Fast Hybrid Schemes for Fractional Riccati Equations (Rough Is Not So Tough) , 2018, Math. Oper. Res..

[53]  N. Touzi,et al.  Contingent Claims and Market Completeness in a Stochastic Volatility Model , 1997 .

[54]  Archil Gulisashvili,et al.  Large Deviation Principle for Volterra Type Fractional Stochastic Volatility Models , 2017, SIAM J. Financial Math..

[55]  A. Jacquier,et al.  Functional Central Limit Theorems for Rough Volatility , 2017, 1711.03078.

[56]  Hyuk Lee,et al.  Neural algorithm for solving differential equations , 1990 .

[57]  Ioannis Karatzas,et al.  Brownian Motion and Stochastic Calculus , 1987 .

[58]  William A McGhee,et al.  An Artificial Neural Network Representation of the SABR Stochastic Volatility Model , 2018, The Journal of Computational Finance.

[59]  Nizar Touzi,et al.  On viscosity solutions of path dependent PDEs , 2011, 1109.5971.

[60]  Mikko S. Pakkanen,et al.  Decoupling the Short- and Long-Term Behavior of Stochastic Volatility , 2016, 1610.00332.

[61]  Eduardo Abi Jaber,et al.  Lifting the Heston model , 2018, Quantitative Finance.

[62]  Claude Martini,et al.  On VIX futures in the rough Bergomi model , 2017, 1701.04260.

[63]  Daniel Lacker,et al.  Inverting the Markovian projection, with an application to local stochastic volatility models , 2019 .

[64]  David Siska,et al.  Unbiased deep solvers for parametric PDEs , 2018 .

[65]  Almut E. D. Veraart,et al.  Hybrid simulation scheme for volatility modulated moving average fields , 2017, Math. Comput. Simul..

[66]  E. H. Lloyd,et al.  Long-Term Storage: An Experimental Study. , 1966 .

[67]  Peter Parczewski,et al.  Donsker-type theorems for correlated geometric fractional Brownian motions and related processes , 2017 .

[68]  C. Bayer,et al.  Short-time near-the-money skew in rough fractional volatility models , 2017, Quantitative Finance.

[69]  Boualem Djehiche,et al.  Hedging options in market models modulated by the fractional Brownian motion , 2001 .

[70]  Bruno Dupire,et al.  Functional Itô Calculus , 2009 .

[71]  Martin Larsson,et al.  Affine Volterra processes , 2017, The Annals of Applied Probability.

[72]  Huyên Pham,et al.  Deep backward schemes for high-dimensional nonlinear PDEs , 2019 .

[73]  Jia Zhuo,et al.  Monotone schemes for fully nonlinear parabolic path dependent PDEs , 2014, 1402.3930.

[74]  Mathieu Rosenbaum,et al.  Perfect hedging in rough Heston models , 2017, The Annals of Applied Probability.

[75]  H. E. Hurst,et al.  Long-Term Storage Capacity of Reservoirs , 1951 .

[76]  Masaaki Fukasawa,et al.  Asymptotic analysis for stochastic volatility: martingale expansion , 2011, Finance Stochastics.

[77]  Dimitris G. Papageorgiou,et al.  Neural-network methods for boundary value problems with irregular boundaries , 2000, IEEE Trans. Neural Networks Learn. Syst..