A Constructive Approach to Function Realization by Neural Stochastic Differential Equations

07/01/2023

∙

The problem of function approximation by neural dynamical systems has typically been approached in a top-down manner: Any continuous function can be approximated to an arbitrary accuracy by a sufficiently complex model with a given architecture. This can lead to high-complexity controls which are impractical in applications. In this paper, we take the opposite, constructive approach: We impose various structural restrictions on system dynamics and consequently characterize the class of functions that can be realized by such a system. The systems are implemented as a cascade interconnection of a neural stochastic differential equation (Neural SDE), a deterministic dynamical system, and a readout map. Both probabilistic and geometric (Lie-theoretic) methods are used to characterize the classes of functions realized by such systems.

READ FULL TEXT

A Constructive Approach to Function Realization by Neural Stochastic Differential Equations

Stability of stochastic impulsive differential equations: integrating the cyber and the physical of stochastic systems

Learning stochastic dynamical systems with neural networks mimicking the Euler-Maruyama scheme

Stabilized Neural Differential Equations for Learning Constrained Dynamics

Field dynamics inference for local and causal interactions

Data-driven Solution of Stochastic Differential Equations Using Maximum Entropy Basis Functions

Deterministic particle flows for constraining stochastic nonlinear systems

Learning Stochastic Dynamical System via Flow Map Operator

A Constructive Approach to Function Realization by Neural Stochastic Differential Equations

Related Research

Stability of stochastic impulsive differential equations: integrating the cyber and the physical of stochastic systems

Learning stochastic dynamical systems with neural networks mimicking the Euler-Maruyama scheme

Stabilized Neural Differential Equations for Learning Constrained Dynamics

Field dynamics inference for local and causal interactions

Data-driven Solution of Stochastic Differential Equations Using Maximum Entropy Basis Functions

Deterministic particle flows for constraining stochastic nonlinear systems

Learning Stochastic Dynamical System via Flow Map Operator