Wrapped ß-Gaussians with compact support for exact probabilistic modeling on manifolds
| Authors | |
|---|---|
| Publication date | 12-2023 |
| Journal | Transactions on Machine Learning Research |
| Article number | 1351 |
| Volume | Issue number | 2023 |
| Number of pages | 28 |
| Organisations |
|
| Abstract | We introduce wrapped ß-Gaussians, a family of wrapped distributions on Riemannian manifolds, supporting efficient reparametrized sampling, as well as exact density estimation, effortlessly supporting high dimensions and anisotropic scale parameters. We extend Fenchel-Young losses for geometry-aware learning with wrapped ß-Gaussians, and demonstrate the efficacy of our proposed family in a suite of experiments on hypersphere and rotation manifolds: data fitting, hierarchy encoding, generative modeling with variational autoencoders, and multilingual word embedding alignment. |
| Document type | Article |
| Language | English |
| Published at | https://openreview.net/forum?id=KrequDpWzt |
| Other links | https://github.com/ltl-uva/wbg http://jmlr.org/tmlr/papers/ |
| Downloads |
Wrapped ß-Gaussians with compact support for exact probabilistic modeling on manifolds
(Final published version)
|
| Supplementary materials | |
| Permalink to this page | |