What is it about?
Floating-point histograms allow optimal selection of the number of bins and their width, based on the minimum description length principle. They enable the construction of histograms resistant to outliers or heavy-tailed distributions, with accurate density estimation. The accompanying methodology is effective for discovering interesting patterns in the exploratory analysis of large data sets.
Featured Image
Photo by Mike Petrucci on Unsplash
Why is it important?
Histograms are among the most popular methods used in exploratory analysis to summarize univariate distributions. Fully automatic, accurate and scalable histograms are a key feature for gaining a better understanding of your data.
Perspectives
I hope that the method proposed in this paper will help people to discover new insights in areas where histograms could not be easily applied previously
DR Marc Boullé
Orange Labs
Read the Original
This page is a summary of: Floating-point histograms for exploratory analysis of large scale real-world data sets, Intelligent Data Analysis, January 2024, IOS Press,
DOI: 10.3233/ida-230638.
You can read the full text:
Contributors
The following have contributed to this page
