mlsanityData to 7 Oct 2026

Persistently Trained, Diffusion-assisted Energy-based Models

arXiv 2304.10707 ↗First posted 21 Apr 2023stat.ML cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Maximum likelihood (ML) learning for energy-based models (EBMs) is challenging, partly due to non-convergence of Markov chain Monte Carlo.Several variations of ML learning have been proposed, but existing methods all fail to achieve both post-training image generation and proper density estimation. We propose to introduce diffusion data and learn a joint EBM, called diffusion assisted-EBMs, through persistent training (i.e., using persistent contrastive divergence) with an enhanced sampling algorithm to properly sample from complex, multimodal distributions. We present results from a 2D illustrative experiment and image experiments and demonstrate that, for the first time for image data, persistently trained EBMs can it simultaneously achieve long-run stability, post-training image generation, and superior out-of-distribution detection.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 52 references that are in the map. First posted on arXiv 21 Apr 2023.

Builds on

25 of 52 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  8. 2016Wide Residual Networkscited by 3,057
  9. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  10. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  11. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  12. 2016A Theory of Generative ConvNetcited by 174
13 more
  1. 2019Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Modelcited by 147
  2. 2020Learning Energy-Based Models by Diffusion Recovery Likelihoodcited by 122
  3. 2019On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Modelscited by 105
  4. 2020No MCMC for me: Amortized sampling for fast and stable training of energy-based modelscited by 64
  5. 2016Cooperative Training of Descriptor and Generator Networkscited by 60
  6. 2016Deep Directed Generative Models with Energy-Based Probability Estimationcited by 34
  7. 2018Deep Energy Estimator Networkscited by 34
  8. 2017Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlocited by 33
  9. 2019Exponential Family Estimation via Adversarial Dynamics Embeddingcited by 30
  10. 2020Training Deep Energy-Based Models with f-Divergence Minimizationcited by 29
  11. 2021On Out-of-distribution Detection with Energy-based Modelscited by 17
  12. 2020Accelerating Nonconvex Learning via Replica Exchange Langevin Diffusioncited by 15
  13. 2018Generative Modeling by Inclusive Neural Random Fields with Applications in Image Generation and Anomaly Detectioncited by 9

Built on by

Cited by year

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

3 papers.

  1. 2024Applications of Generative AI (GAI) for Mobile and Wireless Networking: A Surveycited by 9
  2. 2024Learned Reference-based Diffusion Sampling for multi-modal distributionscited by 9
  3. 2025Kolmogorov-Arnold Energy Models: Fast, Interpretable Generative Modelingcited by 1