mlsanityData to 7 Oct 2026

Improving Adversarial Energy-Based Model via Diffusion Process

arXiv 2403.01666 ↗First posted 4 Mar 2024cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Generative models have shown strong generation ability while efficient likelihood estimation is less explored. Energy-based models~(EBMs) define a flexible energy function to parameterize unnormalized densities efficiently but are notorious for being difficult to train. Adversarial EBMs introduce a generator to form a minimax training game to avoid expensive MCMC sampling used in traditional EBMs, but a noticeable gap between adversarial EBMs and other strong generative models still exists. Inspired by diffusion-based models, we embedded EBMs into each denoising step to split a long-generated process into several smaller steps. Besides, we employ a symmetric Jeffrey divergence and introduce a variational posterior distribution for the generator's training to address the main challenges that exist in adversarial EBMs. Our experiments show significant improvement in generation compared to existing adversarial EBMs, while also providing a useful energy function for efficient density estimation.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 59 of its 74 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

59 of 74 references.

References · 59

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  9. 2013Describing Textures in the Wildcited by 2,110
  10. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  12. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
38 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  2. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  3. 2021Variational Diffusion Modelscited by 1,145
  4. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  5. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  6. 2018Which Training Methods for GANs do actually Converge?cited by 672
  7. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  8. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  9. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  10. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  11. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
  12. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  13. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 216
  14. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  15. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  16. 2019Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Modelcited by 147
  17. 2020Improved Contrastive Divergence Training of Energy Based Modelscited by 127
  18. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  19. 2016Energy-based Generative Adversarial Networkcited by 119
  20. 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
  21. 2020Learning Latent Space Energy-Based Prior Modelcited by 104
  22. 2020VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Modelscited by 103
  23. 2020Adversarial score matching and improved sampling for image generationcited by 95
  24. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  25. 2022Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matchingcited by 79
  26. 2019Flow Contrastive Estimation of Energy-Based Modelscited by 75
  27. 2020Generalized Energy Based Modelscited by 73
  28. 2019COCO-GAN: Generation by Parts via Conditional Coordinatingcited by 67
  29. 2020No MCMC for me: Amortized sampling for fast and stable training of energy-based modelscited by 64
  30. 2016Cooperative Training of Descriptor and Generator Networkscited by 60
  31. 2019Maximum Entropy Generators for Energy-Based Modelscited by 55
  32. 2022A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Modelcited by 44
  33. 2020Learning Energy-Based Model with Variational Auto-Encoder as Amortized Samplercited by 43
  34. 2018Divergence Triangle for Joint Training of Generator Model, Energy-based Model, and Inference Modelcited by 34
  35. 2022Learning Iterative Reasoning through Energy Minimizationcited by 32
  36. 2020Joint Training of Variational Auto-Encoder and Latent Energy-Based Modelcited by 30
  37. 2023Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihoodcited by 19
  38. 2023Guiding Energy-based Models via Contrastive Latent Variablescited by 17

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 1.

7 papers.

  1. 2024Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Modelscited by 4
  2. 2025Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamicscited by 3
  3. 2025Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matchingcited by 2
  4. 2025Learning Energy-based Variational Latent Prior for VAEscited by 1
  5. 2024Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximizationcited by 0
  6. 2025Exploring bidirectional bounds for minimax-training of Energy-based modelscited by 0
  7. 2026Comparing SGLD and a fixed-noise Predictor-Corrector adaptation in canonical Joint Energy-Based Models on CIFAR-10cited by 0