autora-experimentalist-falsification 2.1.0

AutoRA Falsification Experimentalist

AutoRA Falsification Experimentalist

The falsification pooler and sampler identify novel experimental conditions $X^{\prime }$ under which the loss $\hat{\mathcal{L}}(M,X,Y,X^{\prime })$ of the best candidate model is predicted to be the highest. This loss is approximated with a multi-layer perceptron, which is trained to predict the loss of a candidate model, $M$, given experiment conditions $X$ and dependent measures $Y$ that have already been probed:

$$\underset{X^{\prime }}{argmax}\hat{\mathcal{L}}(M,X,Y,X^{\prime }).$$

Quickstart Guide

You will need:

• python 3.8 or greater: https://www.python.org/downloads/

Falsification Experimentalist is a part of the autora package:

pip install -U autora["experimentalist-falsification"]

Check your installation by running:

python -c "from autora.experimentalist.falsification import falsification_pool"