Neural Optimal Transport
2022-01-28Code Available2· sign in to hype
Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/iamalexkorotin/neuraloptimaltransportOfficialIn paperpytorch★ 228
- github.com/iamalexkorotin/KernelNeuralOptimalTransportpytorch★ 34
- github.com/milenagazdieva/extremalneuraloptimaltransportpytorch★ 25
Abstract
We present a novel neural-networks-based algorithm to compute optimal transport maps and plans for strong and weak transport costs. To justify the usage of neural networks, we prove that they are universal approximators of transport plans between probability distributions. We evaluate the performance of our optimal transport algorithm on toy examples and on the unpaired image-to-image translation.