Research map / Probabilistic and scientific modeling / Variational and generative sampling
Learning Weighted Submanifolds With Variational Autoencoders and Riemannian Variational Autoencoders
Nina Miolane, Susan Holmes
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use intrinsic rVAE rather than PGA, VAE, or projected VAE | Submanifold learning on synthetic sphere data · Synthetic sphere data | extrinsic 2-Wasserstein distance | Improved |
| Use a geometric prior rather than a Euclidean VAE | Submanifold learning on synthetic sphere data · Synthetic sphere data | extrinsic 2-Wasserstein distance | Improved |
| Use intrinsic rVAE rather than VAE projected back onto the manifold | Submanifold learning on synthetic sphere data · Synthetic sphere data | extrinsic 2-Wasserstein distance | Improved |
| Use variational inference rather than Monte Carlo EM | PPGA inference · PPGA model | inference speed | Improved |
| Use variational inference rather than Monte Carlo EM | PPGA inference · PPGA model | inference accuracy | Hurt |
| Fit a VAE or rVAE with nonzero noise | VAE and rVAE · Synthetic data on R², S², and H₂ | 2-Wasserstein distance to the generating submanifold | Hurt |
| Use a nonlinear decoder rather than a geodesic/linear subspace model | Submanifold learning on synthetic sphere data · Synthetic sphere data | extrinsic 2-Wasserstein distance | Improved |
Closest papers by meaning
- Dilated Convolutional Neural Networks for Sequential Manifold-Valued Data (ICCV 2019 · similarity 0.89)
- Manifold GPLVMs for discovering non-Euclidean latent structure in neural data (NeurIPS 2020 · similarity 0.88)
- Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry (NeurIPS 2025 · similarity 0.87)
- Implicit Gaussian process representation of vector fields over arbitrary latent manifolds (ICLR 2024 · similarity 0.86)
- Exploring the Enigma of Neural Dynamics Through A Scattering-Transform Mixer Landscape for Riemannian Manifold (ICML 2024 · similarity 0.86)
- MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation (NeurIPS 2026 · similarity 0.86)
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.
