acceptodds
Withdrawn from ICLR 2027

Structure-Adaptive Tree Field Integrators

Withdrawn from ICLR 2027, so left out of the paper lists and the map.

Abstract

We present a new class of near-linear algorithms for efficiently integrating general tensor fields defined on trees with distance dependent kernels, the _**St**ructure-**Ad**aptive **T**ree **F**ield **I**ntegrators_ (STAD-TFIs). STAD-TFIs exploit the tree's underlying structure through decompositions built around path backbones and single vertex separators, and use two-dimensional fast Fourier transforms to compute interactions jointly. By exploiting this structural information, STAD-TFIs achieve more computationally efficient integration than their regular efficient _tree field integrators_ (TFI) counterparts. We provide a detailed theoretical analysis of our proposed approach and complement it with an exhaustive empirical evaluation, ranging from speed tests on synthetic trees, through accelerated Sinkhorn-based relaxations of the Optimal Transport algorithms on real meshes, to Topological Attention Transformers for vision tasks. To the best of our knowledge, we provide some of the first results showing that efficient to compute and accurate relaxations of the geodesic Sinkhorn-based solutions of the Optimal Transport problem can be derived by applying fast TFI methods.

Primary area:
learning on graphs and other geometries & topologies
Keywords:
Tree field integration, distance-dependent kernels, fast Fourier transforms, optimal transport, Sinkhorn algorithm, topological attention

Related papers

Discussion (0)

Sign in to comment.