Neural SDEs
Stochastic differential equations with learned functional components.
State the empirical or computational motivation.
Keep continuous-time stochastic structure while learning flexible drift or diffusion maps from data.
Stochastic differential equations with learned functional components.
Expose the proposed mathematical object.
Notation and units
Decimal rates and volatilities, year-fraction time and continuous compounding unless stated otherwise.
Separate evidence from modelling choice.
The proposed method is compared with an established baseline on held-out scenarios.
Parameter uncertainty and extrapolation are reported rather than hidden by one fit metric.
Production use requires independent validation, monitoring and a documented fallback.
“An unstated convention is a future reconciliation break.”— THEQUANTBATEMAN
Define a falsifiable validation target.
Research-stage modelling with challenges in identifiability, stability and governance.
Treat governance as part of the method.
Keep an established Frontier baseline beside the new method and define the scenario in which the fallback takes control.
Ask Bateman about this topic →