Deep signature algorithm for multidimensional path-dependent options

DOI10.1137/23M1571563MaRDI QIDQ6496949zbMATH OpenFDO

Authors Erhan Bayraktar, Feng Qi, Zhaoyu Zhang

Publication date 6 May 2024

Published in SIAM Journal on Financial Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/23M1571563

zbMATH Keywords

Amerasian optionneural networkoptimal stoppingpath-dependent American optionsreflected FBSDEssignature

Mathematics Subject Classification ID

Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Numerical solutions to stochastic differential and integral equations (65C30) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75)

Recommendations

• Deep signature FBSDE algorithm
• Optimal stopping with signatures
• Deep Curve-Dependent PDEs for Affine Rough Volatility
• A new deep neural network algorithm for multiple stopping with applications in options pricing

Cites work

• A course on rough paths. With an introduction to regularity structures
• A numerical scheme for BSDEs
• Analytical valuation of American-style Asian options
• Asymptotic expansion of stochastic flows
• Convergence of solutions of discrete reflected backward SDE's and simulations
• Convergence of the deep BSDE method for coupled FBSDEs
• Deep backward schemes for high-dimensional nonlinear PDEs
• Deep optimal stopping
• Deep signature FBSDE algorithm
• Density of the signature process of fBm
• JDOI variance reduction method and the pricing of American-style options
• Multidimensional stochastic processes as rough paths. Theory and applications.
• Neural network regression for Bermudan option pricing
• Nonparametric regression using deep neural networks with ReLU activation function
• Numerical solution of stochastic differential equations with jumps in finance
• On an optimal stopping problem of an insider
• On probability laws of solutions to differential systems driven by a fractional Brownian motion
• Optimal execution with rough path signatures
• Optimal stopping with signatures
• Pricing Asset Scheduling Flexibility using Optimal Switching
• PRICING OF AMERICAN PATH-DEPENDENT CONTINGENT CLAIMS
• Pricing options under rough volatility with backward SPDEs
• Rate of convergence for the discrete-time approximation of reflected BSDEs arising in switching problems
• Reflected mean-field backward stochastic differential equations. Approximation and associated nonlinear PDEs
• Reflected solutions of backward SDE's, and related obstacle problems for PDE's
• Representations and regularities for solutions to BSDEs with reflections
• Solving high-dimensional optimal stopping problems using deep learning
• Solving high-dimensional partial differential equations using deep learning
• Switching problem and related system of reflected backward SDEs
• Switching problems with controlled randomisation and associated obliquely reflected BSDEs
• System Control and Rough Paths

Cited in

(6)

• Recent developments in machine learning methods for stochastic control and games
• Occupied processes: going with the flow
• Stochastic control with signatures
• Solving high dimensional FBSDE with deep signature techniques with application to nonlinear options pricing
• Deep learning for energy market contracts: Dynkin game with doubly RBSDEs
• On the Pricing of American Options under Stochastic Local Volatility and Stochastic Correlation via the RBSDE Framework

This page was built for publication: Deep signature algorithm for multidimensional path-dependent options

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6496949)