The Construction of Near-optimal Universal Coding of Integers

TL;DR

This paper introduces a near-optimal universal coding scheme for integers, called the ta code, which achieves a minimal expansion factor very close to the theoretical lower bound, improving integer compression efficiency.

Contribution

The paper develops a new probability inequality for decreasing distributions and constructs the ta code, achieving a near-optimal expansion factor of 2.0386, narrowing the bounds for optimal integer coding.

Findings

The ta code achieves an expansion factor of 2.0386.

The minimum expansion factor for optimal UCI is bounded between 2 and 2.0386.

A new probability inequality for decreasing distributions is established.

Abstract

The Universal Coding of Integers~(UCI) is suitable for discrete memoryless sources with unknown probability distributions and infinitely countable alphabet sizes. A UCI is a class of prefix codes for which the ratio of the average codeword length to $\max\{1,H(P)\}$ is within a constant expansion factor \textcolor{red}{$C_{\mathcal{C}}$} for any decreasing probability distribution $P$, where $H(P)$ is the entropy of $P$. For any UCI code $\mathcal{C}$, \emph{the minimum expansion factor} \textcolor{red}{$C_{\mathcal{C}}^{*}$} is defined to represent the infimum of the set of extension factors of $\mathcal{C}$. Each $\mathcal{C}$ has a unique corresponding \textcolor{red}{$C_{\mathcal{C}}^{*}$}, and the smaller \textcolor{red}{$C_{\mathcal{C}}^{*}$} is, the better the compression performance of $\mathcal{C}$ is. The class of UCIs $\mathcal{C}$ (or a family $\{\mathcal{C}_i\}_{i=1}^{\infty}$) that achieves the smallest \textcolor{red}{$C_{\mathcal{C}}^{*}$} is defined as the \emph{optimal UCI}. The best current result is that the range of $C_{\mathcal{C}}^{*}$ for the optimal UCI is $2\leq C_{\mathcal{C}}^{*}\leq 2.5$. In this paper, we prove a tighter probability inequality for decreasing distributions, which serves as a new tool for studying the properties of UCIs. On the basis of this inequality, we prove that there exists a class of near-optimal UCIs, called the $\nu$ code, achieving \textcolor{red}{$C_\nu=2.0386$}. This narrows the range of the minimum expansion factor for the optimal UCI to $2\leq C_{\mathcal{C}}^{*}\leq 2.0386$. We show that the $\nu$ code is currently optimal in terms of the minimum expansion factor. In addition, we propose a new proof showing that the minimum expansion factor of the optimal UCI is lower bounded by $2$.