StPINNs - Deep learning framework for approximation of stochastic differential equations
arXiv:2512.1425815.51 citations
Predicted impact top 71% in NA · last 90 daysOriginality Incremental advance
AI Analysis
This work addresses a domain-specific challenge in computational mathematics and physics, offering a novel method for handling complex stochastic processes.
The authors tackled the problem of approximating solutions to stochastic differential equations driven by Lévy noise by introducing SPINNs, a deep learning framework that systematically provides a mathematical approach for this task.
In this paper, we introduce the SPINNs (stochastic physics-informed neural networks) in a systematic manner. This provides a mathematical framework for approximating the solution of stochastic differential equations (SDEs) driven by Levy noise using artificial neural networks.