Continuous‐time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations

• Published in: Mathematical finance Vol. 34; no. 2; pp. 348 - 424
• Main Authors: Wang, Ziheng, Sirignano, Justin
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01.04.2024
• Subjects: Algorithms; Convergence; Learning; Machine learning; Mathematical models; Network control; Neural networks; Optimal control; Optimization; Parameters; Partial differential equations; Stochastic models; Stochastic processes

Abstract We develop a new continuous‐time stochastic gradient descent method for optimizing over the stationary distribution of stochastic differential equation (SDE) models. The algorithm continuously updates the SDE model's parameters using an estimate for the gradient of the stationary distr...