sbiax is a lightweight library for simulation-based inference (SBI) with a fixed grid of simulations.
Warning
🏗️ Note this repository is under construction, expect changes. 🏗️
In a typical inference problem the data likelihood is unknown. Using density-estimation SBI, we can proceed by
- simulating a set of data and model parameters
${(\boldsymbol{\xi}, \boldsymbol{\pi})_0, ..., (\boldsymbol{\xi}, \boldsymbol{\pi})_N}$ , - obtaining a measurement
$\hat{\boldsymbol{\xi}}$ , - compressing the simulations and the measurements - usually with a neural network or linear compression - to a set of summaries
${(\boldsymbol{x}, \boldsymbol{\pi})_0, ..., (\boldsymbol{x}, \boldsymbol{\pi})_N}$ and$\hat{\boldsymbol{x}}$ , - fitting an ensemble of normalising flow or similar density estimation algorithms (e.g. a Gaussian mixture model),
- the optional optimisation of the parameters for the architecture and fitting hyperparameters of the algorithms,
- sampling the ensemble posterior (using an MCMC sampler if the likelihood is fit directly) conditioned on the datavector to obtain parameter constraints on the parameters of a physical model,
$\boldsymbol{\pi}$ .
sbiax is a code for implementing each of these steps.
Install via
pip install sbiax
and have a look at examples.