Neural Brownian Motion
This provides a rigorous foundation for models where uncertainty attitudes are learnable, potentially impacting fields like finance or AI, but it is incremental as it builds on existing stochastic calculus with neural network integration.
The paper tackles the problem of modeling dynamics under learned uncertainty by introducing Neural Brownian Motion (NBM), a new stochastic process defined with a neural network-driven expectation operator, and proves a representation theorem for its existence and uniqueness as a solution to a stochastic differential equation.
This paper introduces the Neural-Brownian Motion (NBM), a new class of stochastic processes for modeling dynamics under learned uncertainty. The NBM is defined axiomatically by replacing the classical martingale property with respect to linear expectation with one relative to a non-linear Neural Expectation Operator, $\varepsilon^θ$, generated by a Backward Stochastic Differential Equation (BSDE) whose driver $f_θ$ is parameterized by a neural network. Our main result is a representation theorem for a canonical NBM, which we define as a continuous $\varepsilon^θ$-martingale with zero drift under the physical measure. We prove that, under a key structural assumption on the driver, such a canonical NBM exists and is the unique strong solution to a stochastic differential equation of the form ${\rm d} M_t = ν_θ(t, M_t) {\rm d} W_t$. Crucially, the volatility function $ν_θ$ is not postulated a priori but is implicitly defined by the algebraic constraint $g_θ(t, M_t, ν_θ(t, M_t)) = 0$, where $g_θ$ is a specialization of the BSDE driver. We develop the stochastic calculus for this process and prove a Girsanov-type theorem for the quadratic case, showing that an NBM acquires a drift under a new, learned measure. The character of this measure, whether pessimistic or optimistic, is endogenously determined by the learned parameters $θ$, providing a rigorous foundation for models where the attitude towards uncertainty is a discoverable feature.