Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
-
Updated
Oct 20, 2023 - Jupyter Notebook
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
Ying Nian Wu's UCLA Statistical Machine Learning Tutorial on generative modeling.
[NeurIPS 2021] SNIPS: Solving Noisy Inverse Problems Stochastically
The code enables to perform Bayesian inference in an efficient manner through the use of Hamiltonian Neural Networks (HNNs), Deep Neural Networks (DNNs), Neural ODEs, and Symplectic Neural Networks (SympNets) used with state-of-the-art sampling schemes like Hamiltonian Monte Carlo (HMC) and the No-U-Turn-Sampler (NUTS).
Simulation of Langevin dynamics
A demo shows how to combine Langevin dynamics with score matching for generative models.
Code for enumerating and evaluating numerical methods for Langevin dynamics using near-equilibrium estimates of the KL-divergence. Accompanies https://doi.org/10.3390/e20050318
Sampling-based approach to analyse neural networks using TensorFlow
Langevin dynamics based tours of data, in Javascript with R wrapper.
Python solver for the Brownian, Stochastic, or Noisy Differential Equations
A primer on Bayesian Neural Networks. The aim of this reading list is to facilitate the entry of new researchers into the field of Bayesian Deep Learning, by providing an overview of key papers. More details: "A Primer on Bayesian Neural Networks: Review and Debates"
A python code to calculate the Brownian motion of colloidal particles in a time varying force field.
Noise-conditional score networks for music composition by annealed Langevin dynamics
Utilities for determining maximum tolerable timesteps. See https://doi.org/10.3390/e20050318
Advanced machine learning lab
Algorithm for simulating Langevin dynamics and to calculate numerically the work fluctuation theorem.
Includes C++ code to run Markovian Langevin equations in units compatible with the dcTMD correction scripts available at www.moldyn.uni-freiburg.de/software/software.html. In addition, a jupyter notebook can be found which estimates the error of rates at 300 K from T-boosting calculations.
A fork of ESPResSo by Bogdan Tanygin
Course project for SJTU CS385: Machine Learning, advised by Prof. Quanshi Zhang, where I implemented many algorithms from scratch for face recognization and detection.
Add a description, image, and links to the langevin-dynamics topic page so that developers can more easily learn about it.
To associate your repository with the langevin-dynamics topic, visit your repo's landing page and select "manage topics."