Harish-Chandra's admissibility theorem and beyond
Toshiyuki Kobayashi
TL;DR
The article surveys Harish-Chandra's admissibility for restricting representations to maximal compact subgroups and extends these ideas to non-compact subgroups. It develops two general frameworks—$G'$-admissible restriction (discrete, finite multiplicity) and finite/uniform multiplicity properties—to study branching beyond Riemannian settings, with a focus on real spherical spaces and complexifications. The work provides classification criteria, examples, and methods (D-modules, visible actions) that connect branching laws to spectral theory on standard locally homogeneous spaces, including pseudo-Riemannian locally symmetric spaces. It culminates in a geometry-driven approach to spectral analysis on quotients $\Gamma\backslash G/H$, establishing discretely decomposable restrictions with uniformly bounded multiplicities and a subrepresentation-theoretic backbone for understanding the spectrum in non-classical contexts.
Abstract
This article is a record of the lecture at the centennial conference for Harish-Chandra. The admissibility theorem of Harish-Chandra concerns the restrictions of irreducible representations to maximal compact subgroups. In this article, we begin with a brief explanation of two directions for generalizing his pioneering work to {\it{non-compact}} reductive subgroups: one emphasizes discrete decomposability with the finite multiplicity property, while the other focuses on finite/uniformly bounded multiplicity properties. We discuss how the recent representation-theoretic developments in these directions collectively offer a powerful method for the new spectral analysis of standard locally symmetric spaces, extending beyond the classical Riemannian setting.
