mlsanityData to 14 Oct 2026

Autoregressive Quantile Networks for Generative Modeling

arXiv 1806.05575 ↗First posted 14 Jun 2018cs.LG stat.MLcited by 31

Not on the map. Why?

Abstract (arXiv)

We introduce autoregressive implicit quantile networks (AIQN), a fundamentally different approach to generative modeling than those commonly used, that implicitly captures the distribution using quantile regression. AIQN is able to achieve superior perceptual quality and improvements in evaluation metrics, without incurring a loss of sample diversity. The method can be applied to many existing models and architectures. In this work we extend the PixelCNN model with AIQN and demonstrate results on CIFAR-10 and ImageNet using Inception score, FID, non-cherry-picked samples, and inpainting results. We consistently observe that AIQN yields a highly stable algorithm that improves perceptual quality while maintaining a highly diverse distribution.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 3; 2023: 9; 2024: 5; 2025: 6.

31 papers.

Sort:

By area:

  1. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  2. 2021Generative Modeling with Optimal Transport Mapscited by 82
  3. 2021Densely connected normalizing flowscited by 49
  4. 2022A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Modelcited by 44
  5. 2023Distributional GFlowNets with Quantile Flowscited by 28
  6. 2023Diffusion Probabilistic Fieldscited by 28
  7. 2023Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Networkcited by 20
  8. 2023Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihoodcited by 19
  9. 2021Improved Autoregressive Modeling with Distribution Smoothingcited by 18
  10. 2021Probabilistic Time Series Forecasting with Implicit Quantile Networkscited by 17
  11. 2025Relational Conformal Prediction for Correlated Time Seriescited by 11
  12. 2022Inference and Sampling for Archimax Copulascited by 5
19 more
  1. 2022DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Modelscited by 5
  2. 2024Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Modelscited by 5
  3. 2025Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamicscited by 5
  4. 2021Funnels: Exact maximum likelihood with dimensionality reductioncited by 4
  5. 2023Learning to Simulate: Generative Metamodeling via Quantile Regressioncited by 3
  6. 2023CoopInit: Initializing Generative Adversarial Networks via Cooperative Learningcited by 2
  7. 2024Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimizationcited by 2
  8. 2024Deep Generative Quantile Bayescited by 2
  9. 2024Generative Modeling: A Reviewcited by 2
  10. 2021Adapting deep generative approaches for getting synthetic data with realistic marginal distributionscited by 0
  11. 2021Implicit Quantile Neural Networks for Jet Simulation and Correctioncited by 0
  12. 2023Learning Stationary Markov Processes with Contrastive Adjustmentcited by 0
  13. 2023Deep Generative Methods for Producing Forecast Trajectories in Power Systemscited by 0
  14. 2023Combining propensity score methods with variational autoencoders for generating synthetic data in presence of latent sub-groupscited by 0
  15. 2024Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modellingcited by 0
  16. 2025A Data-driven Dynamic Temporal Correlation Modeling Framework for Renewable Energy Scenario Generationcited by 0
  17. 2025Discrete Markov Bridgecited by 0
  18. 2025QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problemscited by 0
  19. 2025From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learningcited by 0