GPU-accelerated Hungarian algorithms for the Linear Assignment Problem

By Ketan Date, R. Nagi. 2016

64 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Computer Networks and Communications, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Soumya Ghosh
2. Yasaman Khazaeni
3. Kristjan H. Greenewald
4. Mikhail Yurochkin

Citations in the corpus

• Bayesian Nonparametric Federated Learning of Neural Networks (2019, background): “We note that (i) this computation only needs to be performed once (ii) the cost matrix construction which appears to be dominating can be trivially sped up using GPUs (iii) recent work demonstrates impressive large scale running times for the Hungarian algorithm using GPUs (Date & Nagi, 2016).”
• GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders (2018, neutral): “Our current implementation performs this step on CPU although a GPU version has been published (Date & Nagi, 2016). computing a differentiable loss.”