mlsanityData to 7 Oct 2026

Towards Healing the Blindness of Score Matching

arXiv 2209.07396 ↗First posted 15 Sep 2022stat.ML cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Score-based divergences have been widely used in machine learning and statistics applications. Despite their empirical success, a blindness problem has been observed when using these for multi-modal distributions. In this work, we discuss the blindness problem and propose a new family of divergences that can mitigate the blindness problem. We illustrate our proposed divergence in the context of density estimation and report improved performance compared to traditional approaches.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 15 Sep 2022.

Builds on

14 of 24 references.

References · 14

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  3. 2021How to Train Your Energy-Based Modelscited by 271
  4. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  5. 2016A Kernel Test of Goodness of Fitcited by 143
  6. 2020Adversarial score matching and improved sampling for image generationcited by 95
  7. 2019Minimum Stein Discrepancy Estimatorscited by 57
  8. 2018Learning deep kernels for exponential family densitiescited by 36
  9. 2020Blindness of score-based methods to isolated components and mixing proportionscited by 33
  10. 2016Measuring Sample Quality with Diffusionscited by 25
  11. 2021Annealed Stein Variational Gradient Descentcited by 24
  12. 2018Spread Divergencecited by 23
2 more
  1. 2022Generalised Bayesian Inference for Discrete Intractable Likelihoodcited by 14
  2. 2021Interpreting diffusion score matching using normalizing flowcited by 9

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 2; 2025: 5.

13 papers.

Sort:

By area:

  1. 2024Diffusive Gibbs Samplingcited by 21
  2. 2025Learning normalized image densities via dual score matchingcited by 17
  3. 2023Robust and Scalable Bayesian Online Changepoint Detectioncited by 16
  4. 2025RNE: plug-and-play diffusion inference-time control and energy-based trainingcited by 16
  5. 2025FEAT: Free energy Estimators with Adaptive Transportcited by 15
  6. 2023Energy Discrepancies: A Score-Independent Loss for Energy-Based Modelscited by 9
  7. 2023Moment Matching Denoising Gibbs Samplingcited by 7
  8. 2024On the Robustness of Kernel Goodness-of-Fit Testscited by 7
  9. 2023Training Energy-Based Normalizing Flow with Score-Matching Objectivescited by 6
  10. 2022Maximum Likelihood Learning of Unnormalized Models for Simulation-Based Inferencecited by 5
  11. 2023Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancycited by 4
  12. 2025A Unified View of Optimal Kernel Hypothesis Testingcited by 4
1 more
  1. 2025Fast and Scalable Score-Based Kernel Calibration Testscited by 2