mlsanityData to 14 Oct 2026

Optimal Budgeted Rejection Sampling for Generative Models

arXiv 2311.00460 ↗First posted 1 Nov 2023cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Rejection sampling methods have recently been proposed to improve the performance of discriminator-based generative models. However, these methods are only optimal under an unlimited sampling budget, and are usually applied to a generator trained independently of the rejection procedure. We first propose an Optimal Budgeted Rejection Sampling (OBRS) scheme that is provably optimal with respect to textitany f-divergence between the true distribution and the post-rejection distribution, for a given sampling budget. Second, we propose an end-to-end method that incorporates the sampling scheme into the training procedure to further enhance the model's overall performance. Through experiments and supporting theory, we show that the proposed methods are effective in significantly improving the quality and diversity of the samples.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 1 Nov 2023.

Builds on

19 of 26 references.

References · 19

  1. 2022Generative Adversarial Networkscited by 5,627
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  4. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
  5. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  6. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  7. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  8. 2018Assessing Generative Models via Precision and Recallcited by 406
  9. 2016Adversarially Learned Inferencecited by 216
  10. 2022Refining Generative Process with Discriminator Guidance in Score-based Diffusion Modelscited by 100
  11. 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
  12. 2018Discriminator Rejection Samplingcited by 49
7 more
  1. 2020Refining Deep Generative Models via Discriminator Gradient Flowcited by 45
  2. 2021Resampling Base Distributions of Normalizing Flowscited by 42
  3. 2018Metropolis-Hastings Generative Adversarial Networkscited by 41
  4. 2019Discriminator optimal transportcited by 25
  5. 2023TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Modelscited by 14
  6. 2023Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flowscited by 9
  7. 2021Latent reweighting, an almost free improvement for GANscited by 6

Built on by

Cited by year (2026 to 14 Oct)

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

5 papers.

  1. 2025Improving Diversity in Language Models: When Temperature Fails, Change the Losscited by 7
  2. 2026Jackpot: Optimal Budgeted Rejection Sampling for Extreme Actor-Policy Mismatch Reinforcement Learningcited by 5
  3. 2025Improving Discriminator Guidance in Diffusion Modelscited by 2
  4. 2026Multimodal Diffusion to Mutually Enhance Polarized Light and Low Resolution EBSD Datacited by 0
  5. 2026Implicit Variational Rejection Samplingcited by 0