AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Learning Weighted Submanifolds With Variational Autoencoders and Riemannian Variational Autoencoders

Nina Miolane, Susan Holmes

CVPR 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 16 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use intrinsic rVAE rather than PGA, VAE, or projected VAESubmanifold learning on synthetic sphere data · Synthetic sphere dataextrinsic 2-Wasserstein distanceImproved
Use a geometric prior rather than a Euclidean VAESubmanifold learning on synthetic sphere data · Synthetic sphere dataextrinsic 2-Wasserstein distanceImproved
Use intrinsic rVAE rather than VAE projected back onto the manifoldSubmanifold learning on synthetic sphere data · Synthetic sphere dataextrinsic 2-Wasserstein distanceImproved
Use variational inference rather than Monte Carlo EMPPGA inference · PPGA modelinference speedImproved
Use variational inference rather than Monte Carlo EMPPGA inference · PPGA modelinference accuracyHurt
Fit a VAE or rVAE with nonzero noiseVAE and rVAE · Synthetic data on R², S², and H₂2-Wasserstein distance to the generating submanifoldHurt
Use a nonlinear decoder rather than a geodesic/linear subspace modelSubmanifold learning on synthetic sphere data · Synthetic sphere dataextrinsic 2-Wasserstein distanceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy