Research map / Probabilistic and scientific modeling / Variational and generative sampling
Bi-level Score Matching for Learning Energy-based Latent Variable Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| increase gradient unrolling steps N from 0 to 10 (ablation) | BiDSM · Frey face GRBM | test log-likelihood: 107.59 -> 125.72 | Helped |
| increase gradient unrolling steps N from 0 to 10 (ablation) | BiDSM · Frey face GRBM | test Fisher divergence: -5474.52 -> -5800.17 | Helped |
| BiDSM (N>=5) vs exact-posterior DSM | GRBM · Frey face | test log-likelihood: 129.23 vs 125.72 | No clear effect |
| increase posterior update steps K from 0 to 20 (ablation) | BiSM · Frey face GRBM | ||phi0 - phi*||: 1.38 -> 0.87 | Helped |
| add latent variables via BiMDSM to MDSM EBM | MDSM deep EBM · CIFAR10 | FID | Helped |
| BiSSM/BiDSM vs SM baselines, CD and NCE on GRBM | GRBM · checkerboard | density fit / test log-likelihood | No clear effect |
Closest papers by meaning
- Learning normalized image densities via dual score matching (NeurIPS 2025 · similarity 0.86)
- Joint Learning of Energy-based Models and their Partition Function (ICML 2025 · similarity 0.85)
- Batch and match: black-box variational inference with a score-based divergence (ICML 2024 · similarity 0.84)
- Learning Latent Space Hierarchical EBM Diffusion Models (ICML 2024 · similarity 0.84)
- Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences (NeurIPS 2026 · similarity 0.84)
- Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization (ICLR 2024 · similarity 0.84)
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.