Tight complexity bounds for diagram commutativity verification

A diagram $\mathcal{D} = (G, l)$ over a monoid $M$ is an oriented graph $G = (V, E)$ endowed with a labeling $l\colon E \to M$. A diagram is commutative if and only if for any two oriented paths with the same endpoints, the products in $M$ of their edge labels coincide. We propose the first asymptotically optimal algorithm for diagram commutativity verification applicable to all graph families. For graphs with $\lvert V\rvert \preceq \lvert E\rvert \preceq \lvert V\rvert^2$, which covers most practically relevant cases, our algorithm runs in $$O\bigl(|V|\,|E|\bigr) \cdot \bigl(T_{\mathrm{equal}} + T_{\mathrm{multi}}\bigr)$$ time; here $T_{\mathrm{equal}}$ and $T_{\mathrm{multi}}$ denote the times to perform an equality check and a multiplication in $M$, respectively. We also establish new lower bounds on the numbers of equality checks and multiplications necessary for commutativity verification, which asymptotically match our algorithm's cost and thus prove its tightness.