One-Shot Learning of Stochastic Differential Equations with Data Adapted Kernels

Matthieu Darcy, Boumediene Hamzi, Giulia Livieri +2

We consider the problem of learning Stochastic Differential Equations of the form $d{X}_t=f(X_t)dt+\sigma (X_t)d{W}_t$ from one sample trajectory. This problem is more challenging than le…