Obtaining trees of tangles from tangle-tree duality
Christian Elbracht, Jay Lilian Kneip, Maximilian Teegen
TL;DR
The paper unifies tree-of-tangles results with the tangle-tree duality theorem in abstract separation systems, enabling derivations of tree structures that distinguish profile collections and providing degree-bounding capabilities. It strengthens the tangle-tree duality framework and develops tools such as splices, shifting, and efficient distinguishers to construct nested separator trees that efficiently separate multiple profiles, including those of mixed orders. The authors introduce a sequence of refinements—from structurally submodular to distributive universes and strongly robust profiles—to extend tree-of-tangles results to tangles of different orders and to bound node degrees. The work thereby bridges core pillars of tangle theory, offering practical methods to obtain trees of tangles with controlled complexity across orders and settings, with implications for generalizations beyond graphs and matroids.
Abstract
We demonstrate the versatility of the tangle-tree duality theorem for abstract separation systems by using it to prove tree-of-tangles theorems. This approach allows us to strengthen some of the existing tree-of-tangles theorems by bounding the node degrees in them. We also present a slight strengthening and simplified proof of the duality theorem, which allows us to derive a tree-of-tangles theorem also for tangles of different orders.
