Skip to Main content Skip to Navigation
Conference papers

Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions

Abstract : By building upon the recent theory that estab- lished the connection between implicit generative modeling (IGM) and optimal transport, in this study, we propose a novel parameter-free algo- rithm for learning the underlying distributions of complicated datasets and sampling from them. The proposed algorithm is based on a functional optimization problem, which aims at finding a measure that is close to the data distribution as much as possible and also expressive enough for generative modeling purposes. We formulate the problem as a gradient flow in the space of proba- bility measures. The connections between gradi- ent flows and stochastic differential equations let us develop a computationally efficient algorithm for solving the optimization problem. We provide formal theoretical analysis where we prove finite- time error guarantees for the proposed algorithm. To the best of our knowledge, the proposed algo- rithm is the first nonparametric IGM algorithm with explicit theoretical guarantees. Our experi- mental results support our theory and show that our algorithm is able to successfully capture the structure of different types of data distributions.
Document type :
Conference papers
Complete list of metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal.inria.fr/hal-02191302
Contributor : Antoine Liutkus <>
Submitted on : Tuesday, July 23, 2019 - 2:02:18 PM
Last modification on : Friday, October 9, 2020 - 8:40:11 AM

File

icml_2019_sketchmcmc.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

  • HAL Id : hal-02191302, version 1

Citation

Antoine Liutkus, Umut Imşekli, Szymon Majewski, Alain Durmus, Fabian-Robert Stöter. Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions. 36th International Conference on Machine Learning (ICML), Jun 2019, Long Beach, United States. ⟨hal-02191302⟩

Share

Metrics

Record views

118

Files downloads

924