# Constraining the Parameters of High-Dimensional Models with Active Learning

## TL;DR

This paper demonstrates that active learning techniques can efficiently explore high-dimensional parameter spaces in physical models, reducing computational costs and improving model constraints in fields like particle physics.

## Contribution

It introduces the use of active learning methods, specifically query-by-committee and query-by-dropout-committee, to efficiently identify important regions in high-dimensional parameter spaces.

## Key findings

- Active learning reduces the number of simulations needed.
- Methods identify regions around decision boundaries effectively.
- Improved model training with less data.

## Abstract

Constraining the parameters of physical models with $>5-10$ parameters is a widespread problem in fields like particle physics and astronomy. The generation of data to explore this parameter space often requires large amounts of computational resources. The commonly used solution of reducing the number of relevant physical parameters hampers the generality of the results. In this paper we show that this problem can be alleviated by the use of active learning. We illustrate this with examples from high energy physics, a field where simulations are often expensive and parameter spaces are high-dimensional. We show that the active learning techniques query-by-committee and query-by-dropout-committee allow for the identification of model points in interesting regions of high-dimensional parameter spaces (e.g. around decision boundaries). This makes it possible to constrain model parameters more efficiently than is currently done with the most common sampling algorithms and to train better performing machine learning models on the same amount of data. Code implementing the experiments in this paper can be found on GitHub.