mlsanityData to 7 Oct 2026

M-EBM: Towards Understanding the Manifolds of Energy-Based Models

arXiv 2303.04343 ↗First posted 8 Mar 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expensive. In this paper, we present a Manifold EBM (M-EBM) to boost the overall performance of unconditional EBM and Joint Energy-based Model (JEM). Despite its simplicity, M-EBM significantly improves unconditional EBMs in training stability and speed on a host of benchmark datasets, such as CIFAR10, CIFAR100, CelebA-HQ, and ImageNet 32x32. Once class labels are available, label-incorporated M-EBM (M-JEM) further surpasses M-EBM in image generation quality with an over 40% FID improvement, while enjoying improved accuracy. The code can be found at https://github.com/sndnyang/mebm.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 8 Mar 2023.

Builds on

18 of 25 references.

References · 18

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  3. 2016Wide Residual Networkscited by 3,057
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  7. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  8. 2019Residual Flows for Invertible Generative Modelingcited by 256
  9. 2018MixUp as Locally Linear Out-Of-Manifold Regularizationcited by 158
  10. 2020Improved Contrastive Divergence Training of Energy Based Modelscited by 127
  11. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  12. 2019On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Modelscited by 105
6 more
  1. 2020VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Modelscited by 103
  2. 2020Generalized Energy Based Modelscited by 73
  3. 2020No MCMC for me: Amortized sampling for fast and stable training of energy-based modelscited by 64
  4. 2020Training Deep Energy-Based Models with f-Divergence Minimizationcited by 29
  5. 2021JEM++: Improved Techniques for Training JEMcited by 28
  6. 2021Towards Understanding the Generative Capability of Adversarially Robust Classifierscited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024Shedding More Light on Robust Classifiers under the lens of Energy-based Modelscited by 9
  2. 2024Hitchhiker's guide on the relation of Energy-Based Models with other generative models, sampling and statistical physics: a comprehensive reviewcited by 5
  3. 2024Graph Structure Refinement with Energy-based Contrastive Learningcited by 3
  4. 2025Understanding Adversarial Training with Energy-based Modelscited by 2
  5. 2025Your Classifier Can Do More: Towards Balancing the Gaps in Classification, Robustness, and Generationcited by 1
  6. 2026A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Modelscited by 1