19.01.2026 15:00 Syoiti Ninomiya:
Architectures of high-order deep neural networks and weak approximation schemes for SDEsMI 03.06.011 (Boltzmannstr. 3, 85748 Garching)
New deep neural network architectures based on high-order weak approximation algorithms for stochastic differential equations (SDEs) are proposed. The core of these architectures is formed by high-order weak approximation algorithms of the explicit Runge--Kutta type, in which the approximation is realised solely through iterative compositions and linear combinations of the vector fields of the target SDEs.