Hierarchical clustering with deep Q-learning

TL;DR

This paper introduces a novel hierarchical clustering method that integrates deep Q-learning to improve cluster prediction accuracy in high energy physics data analysis.

Contribution

It presents a new approach combining hierarchical clustering with deep reinforcement learning, enhancing cluster prediction performance over traditional methods.

Findings

Achieved 83.77% precision in cluster prediction

Demonstrated effectiveness on a dataset of 10,000 nodes

Applied reinforcement learning to improve clustering accuracy

Abstract

The reconstruction and analyzation of high energy particle physics data is just as important as the analyzation of the structure in real world networks. In a previous study it was explored how hierarchical clustering algorithms can be combined with kt cluster algorithms to provide a more generic clusterization method. Building on that, this paper explores the possibilities to involve deep learning in the process of cluster computation, by applying reinforcement learning techniques. The result is a model, that by learning on a modest dataset of 10; 000 nodes during 70 epochs can reach 83; 77% precision in predicting the appropriate clusters.