Alice Moallemy-Oureh's repositories
LOGML2021-Learning-Latent-Geometries
Project description (Learning Latent Geometries by Søren Hauberg): Latent variable models, such as the variational autoencoder, suffer from the identifiability problem: there is no unique configuration of the latent variables. This is problematic as latent variables are often inspected, e.g., through visualization, to gain insights into the data generating process. The lack of identifiability then raises the risk of misinterpreting the data as conclusions may be drawn from arbitrary latent instantiations. In this project, you will investigate a geometric solution to the identifiability problem that amounts to endowing the latent space with a particular Riemannian metric. You will learn latent representations and compute geodesics accordingly. References: () Latent Space Oddity: on the Curvature of Deep Generative Models Georgios Arvanitidis, Lars Kai Hansen and Søren Hauberg. In International Conference on Learning Representations (ICLR), 2018. () Only Bayes should learn a manifold (on the estimation of differential geometric structure from data)