Langevin algorithms for Markovian Neural Networks and Deep Stochastic control
This work addresses training efficiency for deep neural networks in stochastic control, but it is incremental as it extends known Langevin methods to a specific domain.
The authors tackled the challenge of accelerating training for stochastic control problems by applying Langevin algorithms to neural networks, demonstrating improved performance on tasks like hedging and resource management.
Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases where the neural network is very deep. In this paper we study the possibilities of training acceleration for the numerical resolution of stochastic control problems through gradient descent, where the control is parametrized by a neural network. If the control is applied at many discretization times then solving the stochastic control problem reduces to minimizing the loss of a very deep neural network. We numerically show that Langevin algorithms improve the training on various stochastic control problems like hedging and resource management, and for different choices of gradient descent methods.