Solving high-dimensional optimal stopping problems using deep learning

DOI10.1017/S0956792521000073zbMath1505.91413arXiv1908.01602OpenAlexW2990035425MaRDI QIDQ5014845

Patrick Cheridito, Timo Welti, Arnulf Jentzen, Sebastian Becker

Publication date: 8 December 2021

Published in: European Journal of Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.01602

zbMATH Keywords

optimal stoppingoption pricingcurse of dimensionalityderivative pricingAmerican optiondeep learningfinancial derivativeBermudan option

Mathematics Subject Classification ID

Numerical methods (including Monte Carlo methods) (91G60) Artificial neural networks and deep learning (68T07) Monte Carlo methods (65C05) Stopping times; optimal stopping problems; gambling theory (60G40) Derivative securities (option pricing, hedging, etc.) (91G20)

Related Items

Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space, Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms, Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities, A reinforcement learning approach to optimal execution, Deep empirical risk minimization in finance: Looking into the future, Space-time error estimates for deep neural network approximations for differential equations, Pricing High-Dimensional Bermudan Options with Hierarchical Tensor Formats, Neural network approximation and estimation of classifiers with classification boundary in a Barron class, Deep Weak Approximation of SDEs: A Spatial Approximation Scheme for Solving Kolmogorov Equations, Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing, A deep-genetic algorithm (deep-GA) approach for high-dimensional nonlinear parabolic partial differential equations, Designing universal causal deep learning models: The geometric (Hyper)transformer, An overview on deep learning-based approximation methods for partial differential equations, Neural network regression for Bermudan option pricing, Randomized Optimal Stopping Algorithms and Their Convergence Analysis, Deep combinatorial optimisation for optimal stopping time problems: application to swing options pricing., Connections between deep learning and partial differential equations, Algorithms for solving high dimensional PDEs: from nonlinear Monte Carlo to machine learning, Solving High-Dimensional Optimal Stopping Problems Using Optimization Based Model Order Reduction

Uses Software

• Adam
• DGM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Solving optimal stopping problems via empirical dual optimization
• Multilevel dual approach for pricing American style derivatives
• Pricing of American options in discrete time using least squares estimates with complexity penalties
• Pricing Bermudan options by nonparametric regression: optimal rates of convergence for lower estimates
• Monte Carlo algorithms for optimal stopping and statistical learning
• On the rates of convergence of simulation-based optimization algorithms for optimal stopping problems
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Convergence and biases of Monte Carlo estimates of American option prices using a parametric exercise rule
• An irregular grid approach for pricing high-dimensional American options
• Valuation of the early-exercise price for options using simulations and nonparametric regression
• Pricing American-style securities using simulation
• Multilayer feedforward networks are universal approximators
• Pricing and hedging GMWB in the Heston and in the Black-Scholes with stochastic interest rate models
• Strong convergence for explicit space-time discrete numerical approximation methods for stochastic Burgers equations
• Stochastic calculus for finance. II: Continuous-time models.
• DGM: a deep learning algorithm for solving partial differential equations
• A regression-based smoothing spline Monte Carlo algorithm for pricing American options in discrete time
• Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs
• Additive and multiplicative duals for American option pricing
• A dynamic look-ahead Monte Carlo algorithm for pricing Bermudan options
• Discrete-time approximation and Monte-Carlo simulation of backward stochastic differential equations
• Iterative construction of the optimal Bermudan stopping time
• A regression-based Monte Carlo method to solve backward stochastic differential equations
• Error analysis of the optimal quantization algorithm for obstacle problems.
• Continuous Markov processes and stochastic equations
• An Approximate Dynamic Programming Algorithm for Monotone Value Functions
• Optimal Dual Martingales, Their Analysis, and Application to New Algorithms for Bermudan Products
• Multilevel Simulation Based Policy Iteration for Optimal Stopping--Convergence and Complexity
• A Review on Regression-based Monte Carlo Methods for Pricing American Options
• The duality of optimal exercise and domineering claims: a Doob–Meyer decomposition approach to the Snell envelope
• Enhanced policy iteration for American options via scenario selection
• PRICING OF HIGH-DIMENSIONAL AMERICAN OPTIONS BY NEURAL NETWORKS
• Dual Valuation and Hedging of Bermudan Options
• Improved lower and upper bound algorithms for pricing American options by simulation
• TRUE UPPER BOUNDS FOR BERMUDAN PRODUCTS VIA NON‐NESTED MONTE CARLO
• Pricing American Options: A Duality Approach
• Option Pricing
• Universal approximation bounds for superpositions of a sigmoidal function
• Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives
• Dual Pricing of American Options by Wiener Chaos Expansion
• Stochastic Gradient Descent in Continuous Time
• Monte Carlo valuation of American options
• Pricing high-dimensional Bermudan options using the stochastic grid method
• Solving high-dimensional partial differential equations using deep learning
• Upper bounds for Bermudan options on Markovian data using nonparametric regression and a reduced number of nested Monte Carlo steps
• Implied stopping rules for American basket options from Markovian projection
• Pricing Bermudan Options via Multilevel Approximation Methods
• A PRIMAL–DUAL ALGORITHM FOR BSDES
• A Fast and Accurate FFT-Based Method for Pricing Early-Exercise Options under Lévy Processes
• Valuing American Options by Simulation: A Simple Least-Squares Approach
• Deep optimal stopping
• A METHOD FOR PRICING AMERICAN OPTIONS USING SEMI‐INFINITE LINEAR PROGRAMMING
• Policy iteration for american options: overview
• Probability theory. A comprehensive course
• Approximation by superpositions of a sigmoidal function
• Stochastic Equations in Infinite Dimensions
• Stochastic differential equations. An introduction with applications.