Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications (MIT 18.337J/6.338J)

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

A component of the DiffEq ecosystem for enabling sensitivity analysis for scientific machine learning (SciML). Optimize-then-discretize, discretize-then-optimize, adjoint methods, and more for ODEs, SDEs, DDEs, DAEs, etc.

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

A library of noise processes for stochastic systems like stochastic differential equations (SDEs) and other systems that are present in scientific machine learning (SciML)

A component of the SciML scientific machine learning ecosystem for optimal control

Repository for the Control of Stochastic Quantum Dynamics with Differentiable Programming paper.

Implementation of "Neural Jump-Diffusion Temporal Point Processes" (ICML 2024 Spotlight)

A thin wrapper over Bridge.jl for the SciML scientific machine learning common interface, enabling new methods for neural stochastic differential equations (neural SDEs)

Work in progress of Finite Dimensional Matching for Neural SDEs implementation.

Neural SDE Climate Risk Framework A PyTorch implementation using Variational Autoencoders (VAEs) and Neural Stochastic Differential Equations (SDEs) to model continuous-time corporate default risk and simulate the impact of climate transition shocks on high-carbon sectors.