Simulation-based inference.
Project description
sbi: simulation-based inference
sbi is a PyTorch package for simulation-based inference. Simulation-based inference is
the process of finding parameters of a simulator from observations.
sbi takes a Bayesian approach and returns a full posterior distribution
over the parameters, conditional on the observations. This posterior can be amortized (i.e.
useful for any observation) or focused (i.e. tailored to a particular observation), with different
computational trade-offs.
sbi offers a simple interface for one-line posterior inference.
from sbi.inference import infer
# import your simulator, define your prior over the parameters
parameter_posterior = infer(simulator, prior, method='SNPE', num_simulations=100)
See below for the available methods of inference, SNPE, SNRE and SNLE.
Installation
sbi requires Python 3.6 or higher. It can be installed using pip:
$ pip install sbi
We recommend to use a conda virtual
environment (Miniconda installation instructions). If conda is installed on the system, an environment for
installing sbi can be created as follows:
# Create an environment for sbi (indicate Python 3.6 or higher); activate it
$ conda create -n sbi_env python=3.6 && conda activate sbi_env
To test the installation, drop into a python prompt and run
from sbi.examples.minimal import simple
posterior = simple()
print(posterior)
Inference Algorithms
The following algorithms are currently available:
Sequential Neural Posterior Estimation (SNPE)
SNPE_CorAPTfrom Greenberg D, Nonnenmacher M, and Macke J Automatic Posterior Transformation for likelihood-free inference (ICML 2019).
Sequential Neural Likelihood Estimation (SNLE)
SNLE_Aor justSNLfrom Papamakarios G, Sterrat DC and Murray I Sequential Neural Likelihood (AISTATS 2019).
Sequential Neural Ratio Estimation (SNRE)
-
SNRE_AorAALRfrom Hermans J, Begy V, and Louppe G. Likelihood-free Inference with Amortized Approximate Likelihood Ratios (ICML 2020). -
SNRE_BorSREfrom Durkan C, Murray I, and Papamakarios G. On Contrastive Learning for Likelihood-free Inference (ICML 2020).
Feedback and Contributions
We would like to hear how sbi is working for your inference problems as well as receive bug reports, pull requests and other feedback (see
contribute).
Acknowledgements
sbi is the successor (using PyTorch) of the
delfi package. It was started as a fork of Conor
M. Durkan's lfi. sbi runs as a community project; development is coordinated at the
mackelab. See also credits.
Support
sbi has been developed in the context of the ADIMEM
grant, project A. ADIMEM is a
BMBF grant awarded to groups at the Technical University of Munich, University of
Tübingen and Research Center caesar of the Max Planck Gesellschaft.
License
AGPLv3
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file sbi-0.11.1.tar.gz.
File metadata
- Download URL: sbi-0.11.1.tar.gz
- Upload date:
- Size: 753.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/47.3.1.post20200616 requests-toolbelt/0.9.1 tqdm/4.47.0 CPython/3.7.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 80d52bd6030d9628e65c5d11ff9c430e9d91e4ad0adb0b4fcb695da2ebd3e4a3 |
|
| MD5 | f5ceb6049dd69d5051501ee328b32a1c |
|
| BLAKE2b-256 | 9052029465dfcc7e373fe7646e323f997ea9a202c3cc8f27870db84671a23493 |
File details
Details for the file sbi-0.11.1-py2.py3-none-any.whl.
File metadata
- Download URL: sbi-0.11.1-py2.py3-none-any.whl
- Upload date:
- Size: 113.9 kB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/47.3.1.post20200616 requests-toolbelt/0.9.1 tqdm/4.47.0 CPython/3.7.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 8562a459fea76c758a1e1191fe932a904e33b279a01cd60663120222214967d1 |
|
| MD5 | 31aa8f0273eca3f6a0f35778309696bd |
|
| BLAKE2b-256 | 8e431b5fbe9cb2be9e52321605fa2bf16805661b64c78bc3743e3aca2fb6dea2 |
