Constraining the Parameters of High-Dimensional Models with Active Learning

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.

References in corpus (4)

• A Supersymmetry Primer
• SOFTSUSY: a program for calculating supersymmetric spectra
• Summary of the ATLAS experiment's sensitivity to supersymmetry after LHC Run 1 - interpreted in the phenomenological MSSM
• The BSM-AI project: SUSY-AI - Generalizing LHC limits on Supersymmetry with Machine Learning

Cited by in corpus (17)

• Searches for the BSM scenarios at the LHC using decision tree based machine learning algorithms: A comparative study and review of Random Forest, Adaboost, XGboost and LightGBM frameworks
• Bayesian Neural Networks for Fast SUSY Predictions
• Exploring Parameter Spaces with Artificial Intelligence and Machine Learning Black-Box Optimisation Algorithms
• Mapping out the thermodynamic stability of a QCD equation of state with a critical point using active learning
• Exploration of Parameter Spaces Assisted by Machine Learning
• Active learning BSM parameter spaces
• Mixture-of-theories Training: Can We Find New Physics and Anomalies Better by Mixing Physical Theories?
• Combining Evolutionary Strategies and Novelty Detection to go Beyond the Alignment Limit of the $Z_3$ 3HDM
• Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models
• Uncertainties associated with GAN-generated datasets in high energy physics
• Active Learning for Computationally Efficient Distribution of Binary Evolution Simulations
• Probing intractable beyond-standard-model parameter spaces armed with Machine Learning
• Fast multilabel classification of HEP constraints with deep learning
• Active Learning in Physics: From 101, to Progress, and Perspective
• Quantum Active Learning
• Exploring Scotogenic Parameter Spaces and Mapping Uncharted Dark Matter Phenomenology with Multi-Objective Search Algorithms
• Exploring the BSM parameter space with Neural Network aided Simulation-Based Inference