# Fractional norms and quasinorms do not help to overcome the curse of dimensionality

arXiv: https://arxiv.org/abs/2004.14230 · HTML: https://mlsanity.com/paper/2004.14230/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 13 of 13)

- [Scikit-dimension: a Python package for intrinsic dimension estimation](https://mlsanity.com/paper/2109.02596/) (2021)
- [Multi-metrics adaptively identifies backdoors in Federated learning](https://mlsanity.com/paper/2303.06601/) (2023)
- [Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2211.06660/) (2022)
- [High-dimensional separability for one- and few-shot learning](https://mlsanity.com/paper/2106.15416/) (2021)
- [Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities](https://mlsanity.com/paper/2212.10017/) (2022)
- [Robust estimation of the intrinsic dimension of data sets with quantum cognition machine learning](https://mlsanity.com/paper/2409.12805/) (2024)
- [Ordinal Classification with Distance Regularization for Robust Brain Age Prediction](https://mlsanity.com/paper/2403.10522/) (2023)
- [How I learned to stop worrying and love the curse of dimensionality: an appraisal of cluster validation in high-dimensional spaces](https://mlsanity.com/paper/2201.05214/) (2022)
- [Complexity Scaling Laws for Neural Models using Combinatorial Optimization](https://mlsanity.com/paper/2506.12932/) (2025)
- [An Informational Space Based Semantic Analysis for Scientific Texts](https://mlsanity.com/paper/2205.15696/) (2022)
- [Domain Adaptation Principal Component Analysis: base linear method for learning with out-of-distribution data](https://mlsanity.com/paper/2208.13290/) (2022)
- [When fractional quasi p-norms concentrate](https://mlsanity.com/paper/2505.19635/) (2025)
- [Do You Even Need More Data? Rethinking LLM Deployment for Label-Scarce Tabular Classification with TabLens](https://mlsanity.com/paper/2605.24417/) (2026)

## Abstract (arXiv)

The curse of dimensionality causes the well-known and widely discussed problems for machine learning methods. There is a hypothesis that using of the Manhattan distance and even fractional quasinorms lp (for p less than 1) can help to overcome the curse of dimensionality in classification problems. In this study, we systematically test this hypothesis. We confirm that fractional quasinorms have a greater relative contrast or coefficient of variation than the Euclidean norm l2, but we also demonstrate that the distance concentration shows qualitatively the same behaviour for all tested norms and quasinorms and the difference between them decays as dimension tends to infinity. Estimation of classification quality for kNN based on different norms and quasinorms shows that a greater relative contrast does not mean better classifier performance and the worst performance for different databases was shown by different norms (quasinorms). A systematic comparison shows that the difference of the performance of kNN based on lp for p=2, 1, and 0.5 is statistically insignificant.