All Projects → brain-research → L2hmc

brain-research / L2hmc

Licence: apache-2.0
TensorFlow implementation for training MCMC samplers from the paper: Generalizing Hamiltonian Monte Carlo with Neural Network

Projects that are alternatives of or similar to L2hmc

Data Science Tutorial
Code material for a data science tutorial
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
Psi4numpy
Combining Psi4 and Numpy for education and development.
Stars: ✭ 170 (-1.16%)
Mutual labels:  jupyter-notebook
Amazon Sagemaker Architecting For Ml
Materials for a 2-day instructor led course on applying machine learning
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
Tensorflow Safari Course
Exercises and solutions to accompany my Safari course introducing TensorFlow.
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
Sort Google Scholar
Sorting Google Scholar search results based on the number of citations
Stars: ✭ 170 (-1.16%)
Mutual labels:  jupyter-notebook
Pdftableextract
PDFTableExtract
Stars: ✭ 172 (+0%)
Mutual labels:  jupyter-notebook
Ipywebrtc
WebRTC for Jupyter notebook/lab
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
100 Days Of Ml Code
A day to day plan for this challenge. Covers both theoritical and practical aspects
Stars: ✭ 172 (+0%)
Mutual labels:  jupyter-notebook
Pandas Tutorial
Material for the pandas tutorial at EuroScipy 2016
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
Ditching Excel For Python
Functionalities in Excel translated to Python
Stars: ✭ 172 (+0%)
Mutual labels:  jupyter-notebook
Dog Project
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
Timesynth
A Multipurpose Library for Synthetic Time Series Generation in Python
Stars: ✭ 170 (-1.16%)
Mutual labels:  jupyter-notebook
Awesome Dl Projects
This is a collection of the code that accompanies the reports in The Gallery by Weights & Biases.
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
Alpha Mind
quantitative security portfolio analysis. The analysis pipeline including data storage abstraction, alpha calculation, ML based alpha combining and portfolio calculation.
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
Cinic 10
A drop-in replacement for CIFAR-10.
Stars: ✭ 172 (+0%)
Mutual labels:  jupyter-notebook
Mlbox
Machine Learning Algorithms implementations
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
Sklearn pycon2013
Files for my scikit-learn tutorial at PyCon 2013
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook
Thai2fit
ULMFit Language Modeling, Text Feature Extraction and Text Classification in Thai Language. Created as part of pyThaiNLP
Stars: ✭ 172 (+0%)
Mutual labels:  jupyter-notebook
Lecture Source Py
Source files for "Lectures in Quantitative Economics" -- Python version
Stars: ✭ 172 (+0%)
Mutual labels:  jupyter-notebook
Asrframe
An Automatic Speech Recognition Frame ,一个中文语音识别的完整框架, 提供了多个模型
Stars: ✭ 171 (-0.58%)
Mutual labels:  jupyter-notebook

L2HMC: Automatic Training of MCMC Samplers

TensorFlow open source implementation for training MCMC samplers from the paper:

Generalizing Hamiltonian Monte Carlo with Neural Networks

by Daniel Levy, Matt D. Hoffman and Jascha Sohl-Dickstein


Given an analytically described distributions (implemented as in utils/distributions.py), L2HMC enables training of fast-mixing samplers. We provide an example, in the case of the Strongly-Correlated Gaussian, in the notebook SCGExperiment.ipynb --other details are included in the paper.

Contact

Code author: Daniel Levy

Pull requests and issues: @daniellevy

Citation

If you use this code, please cite our paper:

@article{levy2017generalizing,
  title={Generalizing Hamiltonian Monte Carlo with Neural Networks},
  author={Levy, Daniel and Hoffman, Matthew D. and Sohl-Dickstein, Jascha},
  journal={International Conference on Learning Representations},
  year={2018}
}

Note

This is not an official Google product.

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].