Research map / Probabilistic and scientific modeling / Variational and generative sampling
Concrete Score Matching: Generalized Score Matching for Discrete Data
Chenlin Meng, Kristy Choi, Jiaming Song, Stefano Ermon
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 |
|---|---|---|---|
| Use CSM instead of Ratio Matching | MADE · NLTCS | log-likelihood: -6.15 -> -6.13 | Improved |
| Use CSM instead of Ratio Matching | MADE · Plants | log-likelihood: -15.44 -> -14.02 | Improved |
| Use CSM instead of Ratio Matching | MADE · Jester | log-likelihood: -56.49 -> -54.91 | Improved |
| Use CSM instead of Ratio Matching | MADE · Amazon Diaper | log-likelihood: -10.69 -> -11.13 | Hurt |
| Use CSM instead of Ratio Matching | MADE · Amazon Feeding | log-likelihood: -12.09 -> -12.65 | Hurt |
| Use CSM instead of Discrete Marginalization | MADE · Amazon Gifts | log-likelihood: -4.28 -> -4.22 | Improved |
| Use CSM instead of Ratio Matching | MADE · Amazon Media | log-likelihood: -10.22 -> -10.30 | Hurt |
| Use CSM instead of Ratio Matching | MADE · Amazon Toys | log-likelihood: -9.83 -> -9.30 | Improved |
Closest papers by meaning
- Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization (ICML 2025 · similarity 0.86)
- Local Curvature Smoothing with Stein's Identity for Efficient Score Matching (NeurIPS 2024 · similarity 0.86)
- SD-KDE: Score-Debiased Kernel Density Estimation (NeurIPS 2025 · similarity 0.86)
- Score Matching with Missing Data (ICML 2025 · similarity 0.86)
- Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization (ICLR 2024 · similarity 0.85)
- ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection (ICLR 2024 · similarity 0.85)
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.
