PetrMokrov/Large-Scale-Wasserstein-Gradient-Flows
Source code for Large-Scale Wasserstein Gradient Flows (NeurIPS 2021)
This project helps researchers and practitioners in machine learning and statistics efficiently model and simulate complex probability distributions, especially those evolving over time (like diffusion processes). It takes in data that describes a system's initial state or known properties and outputs an approximation of how its probability distribution changes or settles over time. It's designed for quantitative analysts, machine learning engineers, and computational scientists working with stochastic processes.
No commits in the last 6 months.
Use this if you need to accurately approximate complex, high-dimensional probability distributions or simulate diffusion processes and Fokker-Planck equations at scale.
Not ideal if you are looking for a simple, out-of-the-box solution for basic statistical modeling without needing to delve into advanced computational methods.
Stars
42
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
May 08, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PetrMokrov/Large-Scale-Wasserstein-Gradient-Flows"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PythonOT/POT
POT : Python Optimal Transport
recursionpharma/gflownet
GFlowNet library specialized for graph & molecular data
IShengFang/SpectralNormalizationKeras
Spectral Normalization for Keras Dense and Convolution Layers
dfdazac/wassdistance
Approximating Wasserstein distances with PyTorch
iamalexkorotin/NeuralOptimalTransport
PyTorch implementation of "Neural Optimal Transport" (ICLR 2023 Spotlight)