Exploration of Parameter Spaces Assisted by Machine Learning
This work addresses computational bottlenecks in parameter space exploration for researchers in fields like physics, though it appears incremental as it builds on existing ML-assisted sampling approaches.
The authors tackled the problem of efficiently exploring high-dimensional parameter spaces by using neural networks to suggest promising sampling points, reducing the need for computationally expensive evaluations. They demonstrated comparable or better performance than traditional methods like Markov chain Monte Carlo and MultiNest, with a boosted classifier achieving rapid efficiency gains in iterations.
We demonstrate two sampling procedures assisted by machine learning models via regression and classification. The main objective is the use of a neural network to suggest points likely inside regions of interest, reducing the number of evaluations of time consuming calculations. We compare results from this approach with results from other sampling methods, namely Markov chain Monte Carlo and MultiNest, obtaining results that range from comparably similar to arguably better. In particular, we augment our classifier method with a boosting technique that rapidly increases the efficiency within a few iterations. We show results from our methods applied to a toy model and the type II 2HDM, using 3 and 7 free parameters, respectively. The code used for this paper and instructions are publicly available on the web.