Monotonic Differentiable Sorting Networks

Felix Petersen, Christian Borgelt, Hilde Kühne, Oliver Deussen

Publikation: Beitrag in Buch/Bericht/Konferenzband/GesetzeskommentarKonferenzbeitragPeer-reviewed

Abstract

Differentiable sorting algorithms allow training with sorting and ranking supervision, where only the ordering or ranking of samples is known. Various methods have been proposed to address this challenge, ranging from optimal transport-based differentiable Sinkhorn sorting algorithms to making classic sorting networks differentiable. One problem of current differentiable sorting methods is that they are non-monotonic. To address this issue, we propose a novel relaxation of conditional swap operations that guarantees monotonicity in differentiable sorting networks. We introduce a family of sigmoid functions and prove that they produce differentiable sorting networks that are monotonic. Monotonicity ensures that the gradients always have the correct sign, which is an advantage in gradient-based optimization. We demonstrate that monotonic differentiable sorting networks improve upon previous differentiable sorting methods.
OriginalspracheEnglisch
TitelProc 10th International Conference on Learning Representations (ICLR 2022)
PublikationsstatusVeröffentlicht - 25 Apr. 2022

Systematik der Wissenschaftszweige 2012

  • 102 Informatik

Dieses zitieren