Exponents for Concentration of Measure and Isoperimetry in Product Spaces

@article{Yu2022ExponentsFC,
  title={Exponents for Concentration of Measure and Isoperimetry in Product Spaces},
  author={Lei Yu},
  journal={ArXiv},
  year={2022},
  volume={abs/2205.07596}
}
  • Lei Yu
  • Published 16 May 2022
  • Mathematics, Computer Science
  • ArXiv
In this paper, we provide variational formulas for the asymptotic exponents of the concentration function in the product probability space. The variational formulas for the exponents are expressed in terms of relative entropies (which are from information theory) and optimal transport cost functionals (which are from optimal transport theory). Moreover, in the concentration of measure regime, our variational formula is in fact a dimension-free bound on the concentration function, which is valid… 

References

SHOWING 1-10 OF 15 REFERENCES
Concentration of measure and isoperimetric inequalities in product spaces
The concentration of measure phenomenon in product spaces roughly states that, if a set A in a product ΩN of probability spaces has measure at least one half, “most” of the points of Ωn are “close”
An Asymptotic Isoperimetric Inequality
Abstract. For a finite metric space V with a metric $ \rho $, let V n be the metric space in which the distance between (a1, . . ., an) and (b1, . . ., bn) is the sum $ \sum^{n}_{i = 1} \rho (a_i,
A simple proof of the blowing-up lemma
  • K. Marton
  • Mathematics
    IEEE Trans. Inf. Theory
  • 1986
TLDR
Here an information-theoretic proof of the blowing-up lemma, generalizing it to continuous alphabets, is given.
Asymptotics for Strassen's Optimal Transport Problem
TLDR
This paper considers Strassen's version of optimal transport problem, which is, the excess-cost probability is minimize over all couplings of two distributions, and derives large deviation, moderate deviation, and central limit theorems for this problem.
Minimum KL-Divergence on Complements of $L_{1}$ Balls
TLDR
It is shown that D*(v, Q) ≤ Cv2 + O(v3), where C = C(Q) = 1/2 for balanced distributions, thereby providing a kind of reverse Pinsker inequality.
Topics in Optimal Transportation
Introduction The Kantorovich duality Geometry of optimal transportation Brenier's polar factorization theorem The Monge-Ampere equation Displacement interpolation and displacement convexity Geometric
Asymptotical isoperimetric problem
  • R. AhlswedeZhen Zhang
  • Mathematics
    Proceedings of the 1999 IEEE Information Theory and Communications Workshop (Cat. No. 99EX253)
  • 1999
The isoperimetric problem is well known in extremal combinatorial theory. This problem seems very difficult that so far the solutions are known only in some very special cases. The authors interested
Rényi Divergence and Kullback-Leibler Divergence
TLDR
The most important properties of Rényi divergence and Kullback- Leibler divergence are reviewed, including convexity, continuity, limits of σ-algebras, and the relation of the special order 0 to the Gaussian dichotomy and contiguity.
On Exact and ∞-Rényi Common Informations
  • Lei YuV. Tan
  • Computer Science
    2019 IEEE International Symposium on Information Theory (ISIT)
  • 2019
TLDR
This paper establishes the equivalence between the exact and ∞-Rényi common informations, and provides single-letter upper and lower bounds for these two quantities, and observes that for doubly symmetric binary sources, these two common information are strictly larger than Wyner’s.
Identification via compressed data
TLDR
A combined problem of source coding and identification is considered and the authors first review the traditional problem in source coding theory.
...
...