Unbiased deep solvers for linear parametric PDEs
From MaRDI portal
Abstract: We develop several deep learning algorithms for approximating families of parametric PDE solutions. The proposed algorithms approximate solutions together with their gradients, which in the context of mathematical finance means that the derivative prices and hedging strategies are computed simulatenously. Having approximated the gradient of the solution one can combine it with a Monte-Carlo simulation to remove the bias in the deep network approximation of the PDE solution (derivative price). This is achieved by leveraging the Martingale Representation Theorem and combining the Monte Carlo simulation with the neural network. The resulting algorithm is robust with respect to quality of the neural network approximation and consequently can be used as a black-box in case only limited a priori information about the underlying problem is available. We believe this is important as neural network based algorithms often require fair amount of tuning to produce satisfactory results. The methods are empirically shown to work for high-dimensional problems (e.g. 100 dimensions). We provide diagnostics that shed light on appropriate network architectures.
Recommendations
- The deep parametric PDE method and applications to option pricing
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- DGM: a deep learning algorithm for solving partial differential equations
- Solving the Kolmogorov PDE by means of deep learning
- Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
Cites work
- scientific article; zbMATH DE number 1375552 (Why is no real title available?)
- scientific article; zbMATH DE number 1738335 (Why is no real title available?)
- A mean field view of the landscape of two-layer neural networks
- A neural network-based framework for financial model calibration
- A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
- A theoretical analysis of deep neural networks and parametric PDEs
- Analysis of the generalization error: empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
- Calibrating rough volatility models: a convolutional neural network approach
- Convergence of the deep BSDE method for coupled FBSDEs
- DGM: a deep learning algorithm for solving partial differential equations
- DNN expression rate analysis of high-dimensional PDEs: application to option pricing
- Deep backward schemes for high-dimensional nonlinear PDEs
- Deep learning volatility: a deep neural network perspective on pricing and calibration in (rough) volatility models
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
- Gradient convergence of deep learning-based numerical methods for BSDEs
- Machine learning for semi linear PDEs
- Mean field analysis of neural networks: a central limit theorem
- Mean-field Langevin dynamics and energy landscape of neural networks
- Proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients
- Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems
- Risk estimation via regression
- Solving high-dimensional partial differential equations using deep learning
- Solving parabolic stochastic partial differential equations via averaging over characteristics
- Solving the Kolmogorov PDE by means of deep learning
- Stochastic calculus and applications
- Stochastic differential equations. An introduction with applications.
- The steepest descent method for forward-backward SDEs
- Variance Reduction for Simulated Diffusions
- Variance reduction for discretised diffusions via regression
- Variance reduction in Monte Carlo estimators via empirical variance minimization
- Weak approximation of martingale representations
Cited in
(10)- A deep learning approach to the probabilistic numerical solution of path-dependent partial differential equations
- Higher-order error estimates of the discrete-time Clark-Ocone formula
- An overview on deep learning-based approximation methods for partial differential equations
- Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
- The modified MSA, a gradient flow and convergence
- The deep parametric PDE method and applications to option pricing
- Deep Curve-Dependent PDEs for Affine Rough Volatility
- Accelerating SDE simulation through learning of stochastic dynamics
- Deep signature FBSDE algorithm
- Neural network expression rates and applications of the deep parametric PDE method in counterparty credit risk
This page was built for publication: Unbiased deep solvers for linear parametric PDEs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5093244)
