# High-dimensional $p$-norms

4 CLASSIC - Computational Learning, Aggregation, Supervised Statistical, Inference, and Classification
DMA - Département de Mathématiques et Applications - ENS Paris, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt
Abstract : Let $\bX=(X_1, \hdots, X_d)$ be a $\mathbb R^d$-valued random vector with i.i.d.~components, and let $\Vert\bX\Vert_p= ( \sum_{j=1}^d|X_j|^p)^{1/p}$ be its $p$-norm, for $p>0$. The impact of letting $d$ go to infinity on $\Vert\bX\Vert_p$ has surprising consequences, which may dramatically affect high-dimensional data processing. This effect is usually referred to as the {\it distance concentration phenomenon} in the computational learning literature. Despite a growing interest in this important question, previous work has essentially characterized the problem in terms of numerical experiments and incomplete mathematical statements. In the present paper, we solidify some of the arguments which previously appeared in the literature and offer new insights into the phenomenon.
Keywords :
Document type :
Preprints, Working Papers, ...
Domain :

Cited literature [16 references]

https://hal.archives-ouvertes.fr/hal-00879436
Contributor : Gérard Biau <>
Submitted on : Sunday, November 3, 2013 - 8:16:23 PM
Last modification on : Friday, June 12, 2020 - 11:02:06 AM
Document(s) archivé(s) le : Tuesday, February 4, 2014 - 4:28:14 AM

### Files

biau-mason-springer4.pdf
Files produced by the author(s)

### Identifiers

• HAL Id : hal-00879436, version 1
• ARXIV : 1311.0587

### Citation

Gérard Biau, David Mason. High-dimensional $p$-norms. 2013. ⟨hal-00879436⟩

Record views