Research map / Probabilistic and scientific modeling / Variational and generative sampling
Statistical Efficiency of Score Matching: The View from Isoperimetry
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 |
|---|---|---|---|
| Add a sufficient statistic encoding the sparse cut between modes | Score matching in the bimodal exponential-family experiment · Bimodal distribution | fit quality relative to MLE | Hurt |
| Remove the sufficient statistic correlated with the sparse cut (ablation) | Score matching in the bimodal exponential-family experiment · Bimodal distribution | fit quality relative to MLE | Helped |
| Increase the oscillation frequency of the sufficient statistic | Score matching · Unimodal distribution with rapidly oscillating sufficient statistic | parameter-estimation accuracy relative to MLE | Hurt |
| Increase the separation between Gaussian mixture modes | Score matching with a one-hidden-layer tanh network · Mixture of two Gaussians | distribution fit quality | Hurt |
Closest papers by meaning
- Provable benefits of score matching (NeurIPS 2023 · similarity 0.89)
- Dimension-free Score Matching and Time Bootstrapping for Diffusion Models (NeurIPS 2025 · similarity 0.87)
- Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization (ICLR 2024 · similarity 0.87)
- Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance (ICML 2025 · similarity 0.86)
- Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization (ICLR 2024 · similarity 0.86)
- Score Matching with Missing Data (ICML 2025 · 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.