mlsanityData to 7 Oct 2026

Boltzmann Tuning of Generative Models

arXiv 2104.05252 ↗First posted 12 Apr 2021cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The paper focuses on the a posteriori tuning of a generative model in order to favor the generation of good instances in the sense of some external differentiable criterion. The proposed approach, called Boltzmann Tuning of Generative Models (BTGM), applies to a wide range of applications. It covers conditional generative modelling as a particular case, and offers an affordable alternative to rejection sampling. The contribution of the paper is twofold. Firstly, the objective is formalized and tackled as a well-posed optimization problem; a practical methodology is proposed to choose among the candidate criteria representing the same goal, the one best suited to efficiently learn a tuned generative model. Secondly, the merits of the approach are demonstrated on a real-world application, in the context of robust design for energy policies, showing the ability of BTGM to sample the extreme regions of the considered criteria.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 69 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

43 of 69 references.

References · 43

  1. 2017Neural Discrete Representation Learningcited by 4,650
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  4. 2015Variational Inference with Normalizing Flowscited by 2,161
  5. 2014Conditional Generative Adversarial Netscited by 2,152
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2016Density estimation using Real NVPcited by 2,029
  8. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  9. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  10. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  11. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  12. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
31 more
  1. 2016Pixel Recurrent Neural Networkscited by 814
  2. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  3. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  4. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  5. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  6. 2015Importance Weighted Autoencoderscited by 454
  7. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  8. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  9. 2013Black Box Variational Inferencecited by 317
  10. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 280
  11. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  12. 2018A Hierarchical Latent Vector Model for Learning Long-Term Structure in Musiccited by 131
  13. 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
  14. 2019Continuous Hierarchical Representations with Poincar'e Variational Auto-Encoderscited by 111
  15. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  16. 2016Disentangling factors of variation in deep representations using adversarial trainingcited by 87
  17. 2018Taming VAEscited by 85
  18. 2019Generative Models for Effective ML on Private, Decentralized Datasetscited by 85
  19. 2019Mixed-curvature Variational Autoencoderscited by 85
  20. 2017CycleGAN, a Master of Steganographycited by 63
  21. 2018Theory and Experiments on Vector Quantized Autoencoderscited by 55
  22. 2020VFlow: More Expressive Generative Flows with Variational Data Augmentationcited by 38
  23. 2016Variational Boosting: Iteratively Refining Posterior Approximationscited by 36
  24. 2018Are Generative Classifiers More Robust to Adversarial Attacks?cited by 36
  25. 2020Variational Autoencoders with Riemannian Brownian Motion Priorscited by 34
  26. 2018DVAE++: Discrete Variational Autoencoders with Overlapping Transformationscited by 31
  27. 2016Boosting Variational Inferencecited by 22
  28. 2017Gaussian variational approximation with a factor covariance structurecited by 22
  29. 2017Bidirectional Conditional Generative Adversarial Networkscited by 10
  30. 2018Tempered Adversarial Networkscited by 6
  31. 2019Hierarchical Importance Weighted Autoencoderscited by 3

Built on by

Not cited yet.