Neural Expectation Operators

TL;DR

This paper develops a new mathematical framework for neural expectation operators based on quadratic BSDEs, enabling modeling of ambiguity with neural networks under less restrictive conditions.

Contribution

It introduces a well-posedness theorem for quadratic BSDEs with neural network drivers under local Lipschitz conditions, bridging deep learning and stochastic analysis.

Findings

Established well-posedness for neural BSDEs with ReLU activations.

Extended theory to coupled FBSDE systems and particle systems.

Provided constructive methods for neural network architectures to enforce properties.

Abstract

This paper introduces \textbf{Measure Learning}, a paradigm for modeling ambiguity via non-linear expectations. We define Neural Expectation Operators as solutions to Backward Stochastic Differential Equations (BSDEs) whose drivers are parameterized by neural networks. The main mathematical contribution is a rigorous well-posedness theorem for BSDEs whose drivers satisfy a local Lipschitz condition in the state variable $y$ and quadratic growth in its martingale component $z$. This result circumvents the classical global Lipschitz assumption, is applicable to common neural network architectures (e.g., with ReLU activations), and holds for exponentially integrable terminal data, which is the sharp condition for this setting. Our primary innovation is to build a constructive bridge between the abstract, and often restrictive, assumptions of the deep theory of quadratic BSDEs and the world of machine learning, demonstrating that these conditions can be met by concrete, verifiable neural network designs. We provide constructive methods for enforcing key axiomatic properties, such as convexity, by architectural design. The theory is extended to the analysis of fully coupled Forward-Backward SDE systems and to the asymptotic analysis of large interacting particle systems, for which we establish both a Law of Large Numbers (propagation of chaos) and a Central Limit Theorem. This work provides the foundational mathematical framework for data-driven modeling under ambiguity.