Geometrical Insights for Implicit Generative Modeling
| Autor: | Maxime Oquab, Martin Arjovsky, Léon Bottou, David Lopez-Paz |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Computer science
010102 general mathematics 01 natural sciences Measure (mathematics) 010104 statistics & probability Distribution (mathematics) Energy distance Convergence (routing) Applied mathematics 0101 mathematics Parametrization Probability measure Generator (mathematics) Parametric statistics |
| Zdroj: | Braverman Readings in Machine Learning. Key Ideas from Inception to Current State ISBN: 9783319994918 Braverman Readings in Machine Learning |
| DOI: | 10.1007/978-3-319-99492-5_11 |
| Popis: | Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the Maximum Mean Discrepancy criterion. A careful look at the geometries induced by these distances on the space of probability measures reveals interesting differences. In particular, we can establish surprising approximate global convergence guarantees for the 1-Wasserstein distance, even when the parametric generator has a nonconvex parametrization. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|