Teppei Ogihara

Drift Estimation for a Multi-Dimensional L\'evy-Driven Stochastic Differential Equation Using Deep Neural Networks

We develop a non-asymptotic theory for nonparametric drift estimation in discretely observed multi-dimensional L\'evy-driven stochastic differential equations using sparse ReLU neural networks. Under exponential \(\beta\)-mixing and an exponential-tail condition on the L\'evy measure, we establish an oracle inequality...