Name
Title | ||
|---|---|---|
Wasserstein Variational Gradient Descent: From Semi-Discrete Optimal Transport to Ensemble Variational Inference. |
Abstract | ||
|---|---|---|
Particle-based variational inference offers a flexible way of approximating complex posterior distributions with a set of particles. In this paper we introduce a new particle-based variational inference method based on the theory of semi-discrete optimal transport. Instead of minimizing the KL divergence between the posterior and the variational approximation, we minimize a semi-discrete optimal transport divergence. The solution of the resulting optimal transport problem provides both a particle approximation and a set of optimal transportation densities that map each particle to a segment of the posterior distribution. We approximate these transportation densities by minimizing the KL divergence between a truncated distribution and the optimal transport solution. The resulting algorithm can be interpreted as a form of ensemble variational inference where each particle is associated with a local variational approximation. |
Year | Venue | DocType |
|---|---|---|
2018 | arXiv: Machine Learning | Journal |
Volume | Citations | PageRank |
abs/1811.02827 | 0 | 0.34 |
References | Authors | |
13 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Luca Ambrogioni | 1 | 24 | 5.26 |
| Umut Güçlü | 2 | 88 | 10.86 |
| Yagmur Güçlütürk | 3 | 32 | 4.77 |
| Marcel Van Gerven | 4 | 321 | 39.35 |