mlsanityData to 7 Oct 2026

Pixyz: a Python library for developing deep generative models

arXiv 2107.13109 ↗First posted 28 Jul 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

With the recent rapid progress in the study of deep generative models (DGMs), there is a need for a framework that can implement them in a simple and generic way. In this research, we focus on two features of DGMs: (1) deep neural networks are encapsulated by probability distributions, and (2) models are designed and learned based on an objective function. Taking these features into account, we propose a new Python library to implement DGMs called Pixyz. This library adopts a step-by-step implementation method with three APIs, which allows us to implement various DGMs more concisely and intuitively. In addition, the library introduces memoization to reduce the cost of duplicate computations in DGMs to speed up the computation. We demonstrate experimentally that this library is faster than existing probabilistic programming languages in training DGMs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 67 references that are in the map. First posted on arXiv 28 Jul 2021.

Builds on

34 of 67 references.

References · 34

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2015Variational Inference with Normalizing Flowscited by 2,161
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2016Density estimation using Real NVPcited by 2,029
  9. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  10. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  11. 2018World Modelscited by 1,444
  12. 2020Energy-based Out-of-distribution Detectioncited by 1,296
22 more
  1. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  2. 2016Pixel Recurrent Neural Networkscited by 814
  3. 2018Disentangling by Factorisingcited by 614
  4. 2015Generating Sentences from a Continuous Spacecited by 607
  5. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  6. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  7. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  8. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  9. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  10. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
  11. 2019A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithmscited by 136
  12. 2018State Representation Learning for Control: An Overviewcited by 125
  13. 2016Learning in Implicit Generative Modelscited by 124
  14. 2017TensorFlow Distributionscited by 105
  15. 2016Joint Multimodal Learning with Deep Generative Modelscited by 87
  16. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  17. 2018An Introduction to Probabilistic Programmingcited by 62
  18. 2018Temporal Difference Variational Auto-Encodercited by 48
  19. 2016Edward: A library for probabilistic modeling, inference, and criticismcited by 28
  20. 2019Chainer: A Deep Learning Framework for Accelerating the Research Cyclecited by 22
  21. 2019Neuro-SERKET: Development of Integrative Cognitive System through the Composition of Deep Probabilistic Generative Modelscited by 20
  22. 2020Joint Distributions for TensorFlow Probabilitycited by 4

Built on by

Not cited yet.