Rudin-Shapiro-Like Sequences with Maximum Asymptotic Merit Factor

TL;DR

This paper characterizes the seeds that generate Rudin-Shapiro-like sequences with maximum asymptotic merit factor 3, revealing a connection to Golay complementary sequences and introducing the concept of almost-complementary pairs.

Contribution

It provides a complete characterization of seeds achieving maximum asymptotic merit factor, linking them to Golay sequences and extending understanding of low autocorrelation sequences.

Findings

Sequences with maximum merit factor are generated by seeds of length 1 or interleavings of Golay pairs.

Optimal seeds for small lengths are near-Golay interleavings, explaining patterns in previous data.

The concept of almost-complementary pairs clarifies the structure of optimal seeds.

Abstract

Borwein and Mossinghoff investigated the Rudin-Shapiro-like sequences, which are infinite families of binary sequences, usually represented as polynomials. Each family of Rudin-Shapiro-like sequences is obtained from a starting sequence (which we call the seed) by a recursive construction that doubles the length of the sequence at each step, and many sequences produced in this manner have exceptionally low aperiodic autocorrelation. Borwein and Mossinghoff showed that the asymptotic autocorrelation merit factor for any such family is at most $3$, and found the seeds of length $40$ or less that produce the maximum asymptotic merit factor of $3$. The definition of Rudin-Shapiro-like sequences was generalized by Katz, Lee, and Trunov to include sequences with arbitrary complex coefficients, among which are families of low autocorrelation polyphase sequences. Katz, Lee, and Trunov proved that the maximum asymptotic merit factor is also $3$ for this larger class. Here we show that a family of such Rudin-Shapiro-like sequences achieves asymptotic merit factor $3$ if and only if the seed is either of length $1$ or is the interleaving of a pair of Golay complementary sequences. For small seed lengths where this is not possible, the optimal seeds are interleavings of pairs that are as close as possible to being complementary pairs, and the idea of an almost-complementary pair makes sense of remarkable patterns in previously unexplained data on optimal seeds for binary Rudin-Shapiro-like sequences.