Sep 26, 2018 · We present a deep generative model, named Monge-Ampère flow, which builds on continuous-time gradient flow arising from the Monge-Ampère equation in optimal ...
We present a deep generative model, named Monge-Amp`ere flow, which builds on continuous-time gradient flow arising from the Monge-Amp`ere equation in.
Aug 30, 2022 · Monge-Ampere flows outperforms the baselines. On the variational inference task one baseline is used, and the result is compared to the exact known free energy.
Monge-Ampère Flow for Generative Modeling - Semantic Scholar
www.semanticscholar.org › paper › Mon...
This approach brings insights and techniques from Monge-Ampere equation, optimal transport, and fluid dynamics into reversible flow-based generative models ...
PyTorch implementation of “Monge-Ampère Flow for Generative Modeling” arXiv:1809.10188 How to run the code Density estimation of MNIST
Sep 30, 2018 · We present a deep generative model, named Monge-Amp\`ere flow, which builds on continuous-time gradient flow arising from the Monge-Amp\`ere ...
sign in. Article,. Monge-Ampère Flow for Generative Modeling. L. Zhang, W. E, and L. Wang. CoRR, (2018 ). 1. 1. Meta data. BibTeX key: journals/corr/abs-1809 ...
People also ask
What is the theory of generative models?
What do generative models generate?
The correspondence between Monge-Ampère equations and reflector design problems was listed as one of the open problems in [60], and can further be related to.
Feb 17, 2023 · The flow can be used to generate samples from either the base or target, and to estimate their likelihood. In addition, this flow can be ...
Invertible residual networks ICML 2019. Optimal path: Zhang L, Wang L. Monge-ampere flow for generative modeling. arXiv preprint arXiv:1809.10188, 2018.