skolouri / swgmm
Sliced Wasserstein Distance for Learning Gaussian Mixture Models
☆62Updated last year
Alternatives and similar repositories for swgmm:
Users that are interested in swgmm are comparing it to the libraries listed below
- Implementation of the Sliced Wasserstein Autoencoder using PyTorch☆101Updated 6 years ago
- Stochastic algorithms for computing Regularized Optimal Transport☆57Updated 6 years ago
- Code for Sliced Gromov-Wasserstein☆66Updated 5 years ago
- Gabriel Peyré, Marco Cuturi, Justin Solomon, Gromov-Wasserstein Averaging of Kernel and Distance Matrices, Proc. of ICML 2016.☆73Updated 8 years ago
- Source code for the ICML2019 paper "Subspace Robust Wasserstein Distances"☆28Updated 5 years ago
- ☆53Updated 6 years ago
- Sliced Wasserstein Generator☆23Updated 6 years ago
- Implementation of the Sliced Wasserstein Autoencoders☆91Updated 6 years ago
- The Deep Weight Prior, ICLR 2019☆44Updated 3 years ago
- Gaussian Process Prior Variational Autoencoder☆81Updated 6 years ago
- Code for NIPS 2017 spotlight paper: "Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration" by Jason Alt…☆31Updated 7 years ago
- MMD, Hausdorff and Sinkhorn divergences scaled up to 1,000,000 samples.☆54Updated 5 years ago
- Keras implementation of Deep Wasserstein Embeddings☆47Updated 6 years ago
- implements optimal transport algorithms in pytorch☆93Updated 2 years ago
- Tensorflow Implementation of "Large-scale Optimal Transport and Mapping Estimation"(ICLR2018/NIPS 2017 OTML)☆19Updated 6 years ago
- PyTorch implementation of Neural Processes☆88Updated 5 years ago
- Python notebooks for Optimal Transport between Gaussian Mixture Models☆41Updated 3 years ago
- Low-variance, efficient and unbiased gradient estimation for optimizing models with binary latent variables. (ICLR 2019)☆28Updated 5 years ago
- LEARNING LATENT PERMUTATIONS WITH GUMBEL-SINKHORN NETWORKS IMPLEMENTATION WITH PYTORCH☆79Updated last year
- A variational inference method with accurate uncertainty estimation. It uses a new semi-implicit variational family built on neural netwo…☆53Updated 4 months ago
- Learning generative models with Sinkhorn Loss☆28Updated 6 years ago
- Sliced Wasserstein Generator☆37Updated 6 years ago
- Learning Generative Models across Incomparable Spaces (ICML 2019)☆27Updated 4 years ago
- In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represen…☆41Updated 3 years ago
- ☆39Updated 4 years ago
- Sinkhorn Barycenters via Frank-Wolfe algorithm☆24Updated 5 years ago
- Contains the code relative to the paper Partial Gromov-Wasserstein with Applications on Positive-Unlabeled Learning https://arxiv.org/abs…☆21Updated 4 years ago
- Scalable Training of Inference Networks for Gaussian-Process Models, ICML 2019☆41Updated 2 years ago
- Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors☆63Updated 4 years ago
- Learning Autoencoders with Relational Regularization☆45Updated 4 years ago