Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
-
Updated
Aug 17, 2026 - Julia
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
Work in progress of Finite Dimensional Matching for Neural SDEs implementation.
A Deep Learning approach to quantitative volatility modeling. This project implements an Autoregressive Neural Stochastic Differential Equation (Neural SDE) using PyTorch to forecast VIX dynamics, capturing non-linear market regimes and outperforming traditional Heston models.
Add a description, image, and links to the neural-sdes topic page so that developers can more easily learn about it.
To associate your repository with the neural-sdes topic, visit your repo's landing page and select "manage topics."