Research map / Probabilistic and scientific modeling / Variational and generative sampling
Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent
Priyank Jaini, Lars Holdijk, Max Welling
Read the paperCheck 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 |
|---|---|---|---|
| train EBM with equivariant SVGD instead of vanilla SVGD (ablation) | Equivariant EBM · DW-4 | recovered meta-stable states | Improved |
| use equivariant energy model instead of regular energy model (ablation) | EBM with C4 steerable CNN · FashionMNIST (rotated test) | classification accuracy | Improved |
| train equivariant EBM with E-SVGD instead of vanilla SVGD (ablation) | C4 steerable CNN EBM · FashionMNIST (rotated test) | convergence speed of accuracy | Improved |
| use E-SVGD with E-GNN energy to generate C5H8O1 isomers | E-GNN EBM · QM9 | distance/angle distributions | Mixed |
| set RBF kernel bandwidth too high in equivariant SVGD sampling (ablation) | Equivariant SVGD · DW-4 | coverage of meta-stable states | Mixed |
Closest papers by meaning
- Learning (Approximately) Equivariant Networks via Constrained Optimization (NeurIPS 2025 · similarity 0.88)
- Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment (ICML 2025 · similarity 0.87)
- On the hardness of learning under symmetries (ICLR 2024 · similarity 0.87)
- Joint Learning of Energy-based Models and their Partition Function (ICML 2025 · similarity 0.87)
- Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion (NeurIPS 2025 · similarity 0.87)
- Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency (ICML 2024 · 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.
