Automatic Adjoint Differentiation for special functions involving expectations

Code

• github.com/jncbrito/methods
  OfficialIn papernone★ 0

Abstract

We explain how to compute gradients of functions of the form G = 12 _i=1^m (E y_i - C_i)^2, which often appear in the calibration of stochastic models, using Automatic Adjoint Differentiation and parallelization. We expand on the work of arXiv:1901.04200 and give faster and easier to implement approaches. We also provide an implementation of our methods and apply the technique to calibrate European options.

Reproductions