Combining Evolutionary Strategies and Novelty Detection to go Beyond the Alignment Limit of the $Z_3$ 3HDM

TL;DR

This paper introduces a new AI method combining Evolutionary Strategies and Novelty Detection to efficiently explore complex parameter spaces in particle physics models, surpassing traditional sampling methods and uncovering previously overlooked regions.

Contribution

The authors develop a novel AI approach that enhances parameter space exploration in the $Z_3$ 3HDM by integrating Evolutionary Strategies with a novelty reward, enabling deeper and more efficient searches.

Findings

Achieves up to eight orders of magnitude higher sampling efficiency than random sampling.

Enables exploration of previously overlooked parameter regions.

Facilitates discovery of new phenomenological scenarios in the $Z_3$ 3HDM.

Abstract

We present a novel Artificial Intelligence approach for Beyond the Standard Model parameter space scans by augmenting an Evolutionary Strategy with Novelty Detection. Our approach leverages the power of Evolutionary Strategies, previously shown to quickly converge to the valid regions of the parameter space, with a \emph{novelty reward} to continue exploration once converged. Taking the $Z_3$ 3HDM as our Physics case, we show how our methodology allows us to quickly explore highly constrained multidimensional parameter spaces, providing up to eight orders of magnitude higher sampling efficiency when compared with pure random sampling and up to four orders of magnitude when compared to random sampling around the alignment limit. In turn, this enables us to explore regions of the parameter space that have been hitherto overlooked, leading to the possibility of novel phenomenological realisations of the $Z_3$ 3HDM that had not been considered before.