Neural Hamiltonian Operator

TL;DR

This paper introduces the Neural Hamiltonian Operator (NHO), a deep learning framework for solving high-dimensional stochastic control problems via FBSDEs and Pontryagin's Maximum Principle, with theoretical guarantees and analysis.

Contribution

It formalizes the NHO as a neural network-based operator for coupled FBSDEs, providing a rigorous, universal approximation framework and insights into optimization challenges.

Findings

Proves universal approximation capabilities of NHOs.

Frames deep FBSDE methods within statistical inference.

Analyzes optimization challenges in training NHOs.

Abstract

Stochastic control problems in high dimensions are notoriously difficult to solve due to the curse of dimensionality. An alternative to traditional dynamic programming is Pontryagin's Maximum Principle (PMP), which recasts the problem as a system of Forward-Backward Stochastic Differential Equations (FBSDEs). In this paper, we introduce a formal framework for solving such problems with deep learning by defining a \textbf{Neural Hamiltonian Operator (NHO)}. This operator parameterizes the coupled FBSDE dynamics via neural networks that represent the feedback control and an ansatz for the value function's spatial gradient. We show how the optimal NHO can be found by training the underlying networks to enforce the consistency conditions dictated by the PMP. By adopting this operator-theoretic view, we situate the deep FBSDE method within the rigorous language of statistical inference, framing it as a problem of learning an unknown operator from simulated data. This perspective allows us to prove the universal approximation capabilities of NHOs under general martingale drivers and provides a clear lens for analyzing the significant optimization challenges inherent to this class of models.