Lie theory of finite simple groups and the Roth property

TL;DR

This paper explores the Lie algebraic structures on finite groups via noncommutative geometry, focusing on the Killing form and its relation to the Roth property, with results on invertibility and eigenvalues for various groups.

Contribution

It introduces a new criterion linking the Killing form to the Roth property of finite groups and provides computational evidence for simple groups.

Findings

The magnitude of the Killing form is well-defined for all finite groups.

A finite group is Roth iff the Killing form magnitude is not 1/(N-1).

Most finite simple groups are Roth and almost Roth.

Abstract

In noncommutative geometry a `Lie algebra' or bidirectional bicovariant differential calculus on a finite group is provided by a choice of an ad-stable generating subset C stable under inversion. We study the associated Killing form. For the universal calculus associated to C=G \ {e} we show that the magnitude of the Killing form \mu=\sum_{a,b\in C}K^{-1}_{a,b} is defined for all finite groups (even when K is not invertible) and that a finite group is Roth, meaning its conjugation representation contains every irreducible, iff \mu\ is not equal to 1/(N-1), where N is the number of conjugacy classes. We show further that the Killing form is invertible in the Roth case, and that the Killing form restricted to the (N-1)-dimensional subspace of invariant vectors is invertible iff the finite group is almost-Roth group (meaning its conjugation representation has at most one missing irreducible). It is known that most finite simple groups are Roth and that all are almost Roth. At the other extreme from the universal calculus we prove that the generating conjugacy class in the case of the dihedral groups D_{2n} with n odd has invertible Killing form, and the same for the 2-cycles conjugacy class in any S_n. We also compute some eigenvalues of the Killing form in the case of the n-cycles class in S_n. Finally, we verify invertibility of the Killing forms of all real conjugacy classes in all nonabelian finite simple groups to order 75,000, by computer, and we conjecture this to extend to all nonabelian finite simple groups.