ChunyuanLI / Psgld
AAAI & CVPR 2016: Preconditioned Stochastic Gradient Langevin Dynamics (pSGLD)
Stars: ✭ 28
Programming Languages
matlab
3953 projects
Labels
Projects that are alternatives of or similar to Psgld
Bayesplot
bayesplot R package for plotting Bayesian models
Stars: ✭ 276 (+885.71%)
Mutual labels: mcmc
Convchain
Bitmap generation from a single example with convolutions and MCMC
Stars: ✭ 581 (+1975%)
Mutual labels: mcmc
Bayadera
High-performance Bayesian Data Analysis on the GPU in Clojure
Stars: ✭ 342 (+1121.43%)
Mutual labels: mcmc
Boltzmann Machines
Boltzmann Machines in TensorFlow with examples
Stars: ✭ 768 (+2642.86%)
Mutual labels: mcmc
BayesianTutorials
Implementing MCMC sampling from scratch in R for various Bayesian models
Stars: ✭ 75 (+167.86%)
Mutual labels: mcmc
smfsb
Documentation, models and code relating to the 3rd edition of the textbook Stochastic Modelling for Systems Biology
Stars: ✭ 27 (-3.57%)
Mutual labels: mcmc
Pymc3
Probabilistic Programming in Python: Bayesian Modeling and Probabilistic Machine Learning with Aesara
Stars: ✭ 6,214 (+22092.86%)
Mutual labels: mcmc
Torsten
library of C++ functions that support applications of Stan in Pharmacometrics
Stars: ✭ 38 (+35.71%)
Mutual labels: mcmc
Bayesian Neural Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
Stars: ✭ 900 (+3114.29%)
Mutual labels: mcmc
pyaneti
A multi-planet Radial Velocity and Transit modelling software
Stars: ✭ 26 (-7.14%)
Mutual labels: mcmc
Dbda Python
Doing Bayesian Data Analysis, 2nd Edition (Kruschke, 2015): Python/PyMC3 code
Stars: ✭ 502 (+1692.86%)
Mutual labels: mcmc
Owl
Owl - OCaml Scientific and Engineering Computing @ http://ocaml.xyz
Stars: ✭ 919 (+3182.14%)
Mutual labels: mcmc
pSGLD
Preconditioned Stochastic Gradient Langevin Dynamics (pSGLD)
Links: Implementation on TensorFlow Website
Simulation (2D Gaussian Example in Figure 1 of the paper)
- Simulation 1 provides Average Absolute Error of Sample Covariance vs AutoCorrelation Time (ACT)
- Simulation 2 provides first 600 samples from SGLD and pSGLD
Experiments on Deep Neural Networks (Keep updating)
- Start to run 'test_FNN_mnist.m' to test a 2-layer FNN with 400 hidden units each .
- You may also modify line 'linSizes = [400 400 data.outSize]' to other configurations.
Citation
Please cite our AAAI paper if it helps your research:
@inproceedings{pSGLD_AAAI2016,
title={Preconditioned stochastic gradient Langevin dynamics for deep neural networks},
author={Li, Chunyuan and Chen, Changyou and Carlson, David and Carin, Lawrence},
booktitle={AAAI},
Year = {2016}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].