Speaker
Description
A key challenge in the field of AI is to make machine-assisted discovery interpretable, enabling it not only to uncover correlations but also to enhance our physical understanding of the world. A nascent branch of machine learning -- Symbolic Regression (SR) -- aims to discover the optimal functional representations of datasets, producing perfectly interpretable outputs (equations) by construction. I will describe the ambitious project of searching and evaluating function space exhaustively. Coupled to an information-theoretic model selection principle based on minimum description length, our algorithm "Exhaustive Symbolic Regression" is guaranteed to find the simple functions that optimally balance accuracy with simplicity on a dataset. This gives it broad application across science. After detailing the method I will use it to quantify the extent to which state-of-the-art astrophysical theories -- FLRW cosmology, General Relativity and Inflation -- are implied by the current data.
