Uber, May 20th 2020, released a framework for designing experiments within Pyro, its open-source tool for deep probabilistic modelling. The framework leverages machine learning to enable optimal experimental design (OED), a principle-based on information theory that enables the automatic selection of designs for complex experiments. With the framework, experimenters can apply OED to a large class of experimental models, from DNA assays to website and app A/B tests.

https://venturebeat.com/2020/0.....periments/
http://docs.pyro.ai/en/stable/.....b.oed.html

Designing Adaptive Experiments to Study Working Memory
https://pyro.ai/examples/worki.....emory.html

Today's forum question - What rapid quick-fire ideas can be evaluated using the Pyro scripts, tested and re-tested for optimization purposes? I'm interested in fast, quantitative assessments around A/B evaluations of an end-to-end workflow? I'm looking for stress-points and ideas around reducing cognitive load for the user in the enterprise life science domain.