NeurIPS 2020poster41 citations

Disentangling by Subspace Diffusion

David Pfau, Irina Higgins, Alex Botev, Sébastien Racanière

Abstract

We present a novel nonparametric algorithm for symmetry-based disentangling of data manifolds, the Geometric Manifold Component Estimator (GEOMANCER). GEOMANCER provides a partial answer to the question posed by Higgins et al.(2018): is it possible to learn how to factorize a Lie group solely from observations of the orbit of an object it acts on? We show that fully unsupervised factorization of a data manifold is possible

BibTeX
@inproceedings{NEURIPS2020_c9f029a6,
 author = {Pfau, David and Higgins, Irina and Botev, Alex and Racani\`{e}re, S\'{e}bastien},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
 pages = {17403--17415},
 publisher = {Curran Associates, Inc.},
 title = {Disentangling by Subspace Diffusion},
 url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/c9f029a6a1b20a8408f372351b321dd8-Paper.pdf},
 volume = {33},
 year = {2020}
}
Disentangling by Subspace Diffusion · NeurIPS 2020