A high-dimensional CLT in $$\mathcal {W}_2$$ W 2 distance with near optimal convergence rate

A high-dimensional CLT in $$\mathcal {W}_2$$ W 2 distance with near optimal convergence rate Let $$X_1,\ldots ,X_n$$ X 1 , … , X n be i.i.d. random vectors in $$\mathbb {R}^d$$ R d with $$\Vert X_1\Vert \le \beta $$ ‖ X 1 ‖ ≤ β . Then, we show that $$\begin{aligned} \frac{1}{\sqrt{n}}\left( X_1 + \cdots + X_n\right) \end{aligned}$$ 1 n X 1 + ⋯ + X n converges to a Gaussian in quadratic transportation (also known as “Kantorovich” or “Wasserstein”) distance at a rate of $$O \left( \frac{\sqrt{d} \beta \log n}{\sqrt{n}} \right) $$ O d β log n n , improving a result of Valiant and Valiant. The main feature of our theorem is that the rate of convergence is within $$\log n$$ log n of optimal for $$n, d \rightarrow \infty $$ n , d → ∞ . http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Probability Theory and Related Fields Springer Journals

A high-dimensional CLT in $$\mathcal {W}_2$$ W 2 distance with near optimal convergence rate

Loading next page...
 
/lp/springer_journal/a-high-dimensional-clt-in-mathcal-w-2-w-2-distance-with-near-optimal-565OACu0t8
Publisher
Springer Berlin Heidelberg
Copyright
Copyright © 2017 by Springer-Verlag Berlin Heidelberg
Subject
Mathematics; Probability Theory and Stochastic Processes; Theoretical, Mathematical and Computational Physics; Quantitative Finance; Mathematical and Computational Biology; Statistics for Business/Economics/Mathematical Finance/Insurance; Operations Research/Decision Theory
ISSN
0178-8051
eISSN
1432-2064
D.O.I.
10.1007/s00440-017-0771-3
Publisher site
See Article on Publisher Site

Abstract

Let $$X_1,\ldots ,X_n$$ X 1 , … , X n be i.i.d. random vectors in $$\mathbb {R}^d$$ R d with $$\Vert X_1\Vert \le \beta $$ ‖ X 1 ‖ ≤ β . Then, we show that $$\begin{aligned} \frac{1}{\sqrt{n}}\left( X_1 + \cdots + X_n\right) \end{aligned}$$ 1 n X 1 + ⋯ + X n converges to a Gaussian in quadratic transportation (also known as “Kantorovich” or “Wasserstein”) distance at a rate of $$O \left( \frac{\sqrt{d} \beta \log n}{\sqrt{n}} \right) $$ O d β log n n , improving a result of Valiant and Valiant. The main feature of our theorem is that the rate of convergence is within $$\log n$$ log n of optimal for $$n, d \rightarrow \infty $$ n , d → ∞ .

Journal

Probability Theory and Related FieldsSpringer Journals

Published: Mar 24, 2017

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off