mlsanityData to 7 Oct 2026

Hitchhiker's guide on the relation of Energy-Based Models with other generative models, sampling and statistical physics: a comprehensive review

arXiv 2406.13661 ↗First posted 19 Jun 2024cs.LG math-ph math.MPcited by 5

Not on the map. Why?

Abstract (arXiv)

Energy-Based Models have emerged as a powerful framework in the realm of generative modeling, offering a unique perspective that aligns closely with principles of statistical mechanics. This review aims to provide physicists with a comprehensive understanding of EBMs, delineating their connection to other generative models such as Generative Adversarial Networks, Variational Autoencoders, and Normalizing Flows. We explore the sampling techniques crucial for EBMs, including Markov Chain Monte Carlo (MCMC) methods, and draw parallels between EBM concepts and statistical mechanics, highlighting the significance of energy functions and partition functions. Furthermore, we delve into recent training methodologies for EBMs, covering recent advancements and their implications for enhanced model performance and efficiency. This review is designed to clarify the often complex interconnections between these models, which can be challenging due to the diverse communities working on the topic.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 48 of its 131 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

48 of 131 references.

References · 48

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  6. 2016Improved Techniques for Training GANscited by 2,938
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  10. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  11. 2022Diffusion Models in Vision: A Surveycited by 1,008
  12. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
36 more
  1. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  2. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  3. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  4. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  5. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  6. 2021How to Train Your Energy-Based Modelscited by 271
  7. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  8. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 216
  9. 2016A Theory of Generative ConvNetcited by 174
  10. 2020Dynamical Variational Autoencoders: A Comprehensive Reviewcited by 127
  11. 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
  12. 2018Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problemcited by 123
  13. 2022Score-Based Generative Models Detect Manifoldscited by 121
  14. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
  15. 2021GraphEBM: Molecular Graph Generation with Energy-Based Modelscited by 85
  16. 2019Flow Contrastive Estimation of Energy-Based Modelscited by 75
  17. 2020Generalized Energy Based Modelscited by 73
  18. 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
  19. 2023Energy Transformercited by 69
  20. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
  21. 2021Trajectory Prediction with Latent Belief Energy-Based Modelcited by 60
  22. 2021Smooth Normalizing Flowscited by 52
  23. 2017A-NICE-MC: Adversarial Training for MCMCcited by 36
  24. 2019A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trendscited by 26
  25. 2020Energy-based View of Retrosynthesiscited by 24
  26. 2023Learning Manifold Dimensions with Conditional Variational Autoencoderscited by 20
  27. 2022Accelerating Score-based Generative Models with Preconditioned Diffusion Samplingcited by 19
  28. 2023Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approachcited by 17
  29. 2023Efficient Training of Energy-Based Models Using Jarzynski Equalitycited by 15
  30. 2023Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyondcited by 13
  31. 2021Dual Training of Energy-Based Models with Overparametrized Shallow Neural Networkscited by 8
  32. 2021Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effectscited by 7
  33. 2023M-EBM: Towards Understanding the Manifolds of Energy-Based Modelscited by 6
  34. 2023Training Energy-Based Normalizing Flow with Score-Matching Objectivescited by 6
  35. 2023Versatile Energy-Based Probabilistic Models for High Energy Physicscited by 2
  36. 2022Energy-based Generative Models for Target-specific Drug Discoverycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoningcited by 2
  2. 2025Jarzynski Reweighting and Sampling Dynamics for Training Energy-Based Models: Theoretical Analysis of Different Transition Kernelscited by 0
  3. 2026Tutorial on Reasoning for IR & IR for Reasoningcited by 0
  4. 2026Reasoning as Energy Minimization over Structured Latent Trajectoriescited by 0
  5. 2026Cross-Block Conditioning in Deep Boltzmann Machines for Statistical Data Fusioncited by 0