Honeycombs and Sums of Hermitian Matrices, Revisited

Abstract

We give a new proof of the celebrated theorem of Knutson and Tao that the spectra of triples $A,B,A+B$ of Hermitian matrices exactly correspond to positions of boundary rays of honeycombs. Most importantly, our proof gives new insights into why honeycombs are related to Hermitian matrices in the first place. Our proof is axiomatic: We distill four essential properties shared by honeycombs and spectra of Hermitian triples, and show that any two objects sharing these four properties must be equivalent. In this way, we argue that honeycombs are `model organisms' for Hermitian triples: they are families of objects satisfying the same defining properties, but in more obvious ways.

26 pages, 11 figures, comments welcome!