Tensor rank of the determinant and periodic triangulations of $\mathbb{R}^n$

Abstract: We prove that in any $\mathbb{Z}<sup>n$-periodic triangulation of $\mathbb{R}<sup>n$ the number of $\mathbb{Z}<sup>n$-orbits of $n$-dimensional simplices is at least the tensor rank of the $n$th determinant tensor. The latter is known to be at least $\frac{n<sup>{n-1}}{(n-1)!}$, which is approximately $\frac{e^{n}{\sqrt{2\pi} n}}$ for large $n$. The triangulation is not assumed to be geometric, meaning that its simplices can be ``curved''. We also provide lower bounds for general spaces. A simplicial cell complex is a CW-complex glued out of simplices with the attaching maps being simplicial embeddings; this notion generalizes simplicial complexes. We prove that if $X$ is a simplicial cell complex with cohomological classes $\alpha_i\in H<sup>{d_i}(X;\mathbb{Z}_2)$ satisfying [ \alpha_1 \smile \alpha_2 \smile \ldots \smile \alpha_n \neq 0, ] then $X$ has at least $2^n$ simplices of dimension $d_1+d_2+\ldots+d_n$. In particular, a simplicial cell complex homeomorphic to $\mathbb{R} P<sup>n$, $\mathbb{C} P<sup>n$, or $(S<sup>2)<sup>n$, has at least $2^n$ top-dimensional simplices. A crystallization of a manifold is a simplicial cell complex homeomorphic to this manifold and having the least possible number of vertices. We give a short explicit construction of a crystallization and a triangulation of $\mathbb{R}<sup>n/\mathbb{Z}<sup>n$ with $n+1$ and $2<sup>{n+1}-1$ vertices, resp. Triangulations with this many vertices were described before and no smaller triangulation is known.