Pith. sign in

Unbiased deep solvers for linear parametric PDEs

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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.

fields

q-fin.MF 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

On deep calibration of (rough) stochastic volatility models

q-fin.MF · 2019-08-22 · conditional · novelty 6.0

A two-step deep calibration method learns the rough Bergomi implied-volatility map with a small neural network and then calibrates with Levenberg-Marquardt, achieving millisecond calibration.

citing papers explorer

Showing 1 of 1 citing paper.

  • On deep calibration of (rough) stochastic volatility models q-fin.MF · 2019-08-22 · conditional · none · ref 49 · internal anchor

    A two-step deep calibration method learns the rough Bergomi implied-volatility map with a small neural network and then calibrates with Levenberg-Marquardt, achieving millisecond calibration.