mlsanityData to 7 Oct 2026

Implicit Reparameterization Gradients

arXiv 1805.08498 ↗First posted 22 May 2018cs.LG stat.MLcited by 84

Not on the map. Why?

Abstract (arXiv)

By providing a simple and efficient way of computing low-variance gradients of continuous random variables, the reparameterization trick has become the technique of choice for training a variety of latent variable models. However, it is not applicable to a number of important continuous distributions. We introduce an alternative approach to computing reparameterization gradients based on implicit differentiation and demonstrate its broader applicability by applying it to Gamma, Beta, Dirichlet, and von Mises distributions, which cannot be used with the classic reparameterization trick. Our experiments show that the proposed approach is faster and more accurate than the existing gradient estimators for these distributions.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 7; 2023: 16; 2024: 14; 2025: 12; 2026: 13.

84 papers.

Sort:

By area:

  1. 2021Smooth Normalizing Flowscited by 52
  2. 2021Instance-Dependent Partial Label Learningcited by 49
  3. 2021Tractable structured natural gradient descent using local parameterizationscited by 22
  4. 2022One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancementcited by 22
  5. 2021Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Surveycited by 21
  6. 2021Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentationcited by 19
  7. 2021Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Boundcited by 16
  8. 2021Pathologies in priors and inference for Bayesian transformerscited by 13
  9. 2021A unified view of likelihood ratio and reparameterization gradientscited by 12
  10. 2021Storchastic: A Framework for General Stochastic Automatic Differentiationcited by 11
  11. 2021Continuous normalizing flows on manifoldscited by 10
  12. 2021A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Predictioncited by 10
38 more
  1. 2021Model-free Policy Learning with Reward Gradientscited by 9
  2. 2022Reinforcement Learning in Presence of Discrete Markovian Context Evolutioncited by 9
  3. 2023A VAE Approach to Sample Multivariate Extremescited by 9
  4. 2023Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithmscited by 7
  5. 2021Variational Marginal Particle Filterscited by 6
  6. 2022Rectified Max-Value Entropy Search for Bayesian Optimizationcited by 6
  7. 2023Contextual Feature Selection with Conditional Stochastic Gatescited by 6
  8. 2024Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidencecited by 5
  9. 2021Differentiable Feature Selection, a Reparameterization Approachcited by 4
  10. 2022Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variationcited by 4
  11. 2024iMTSP: Solving Min-Max Multiple Traveling Salesman Problem with Imperative Learningcited by 4
  12. 2025Learning to Discover Regulatory Elements for Gene Expression Predictioncited by 4
  13. 2021A Deep Variational Bayesian Framework for Blind Image Deblurringcited by 3
  14. 2021Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modelingcited by 3
  15. 2022RepMode: Learning to Re-parameterize Diverse Experts for Subcellular Structure Predictioncited by 3
  16. 2023Differentiable Rendering with Reparameterized Volume Samplingcited by 3
  17. 2023The Lie-Group Bayesian Learning Rulecited by 3
  18. 2024How to Choose a Reinforcement-Learning Algorithmcited by 3
  19. 2024Stabilizing the Kumaraswamy Distributioncited by 3
  20. 2024FineGates: LLMs Finetuning with Compression using Stochastic Gatescited by 3
  21. 2025Training Diffusion Policies via Prior-Mapping Co-Evolutioncited by 3
  22. 2021Sparse Communication via Mixed Distributionscited by 2
  23. 2021Stochastic Contrastive Learningcited by 2
  24. 2023Learning to Abstract with Nonparametric Variational Information Bottleneckcited by 2
  25. 2024Improving Variational Autoencoder Estimation from Incomplete Data with Mixture Variational Familiescited by 2
  26. 2024Differentiable and Stable Long-Range Tracking of Multiple Posterior Modescited by 2
  27. 2025Deep Variational Sequential Monte Carlo for High-Dimensional Observationscited by 2
  28. 2025BN-Pool: Bayesian Nonparametric Pooling for Graphscited by 2
  29. 2025Negative Binomial Variational Autoencoders for Overdispersed Latent Modelingcited by 2
  30. 2021Stein Latent Optimization for Generative Adversarial Networkscited by 1
  31. 2023Reinforcement Learning for Topic Modelscited by 1
  32. 2023Kernel Density Matrices for Probabilistic Deep Learningcited by 1
  33. 2023Simulation-Based Prior Knowledge Elicitation for Parametric Bayesian Modelscited by 1
  34. 2023Bayesian sparsification for deep neural networks with Bayesian model reductioncited by 1
  35. 2024A Dual Perspective of Reinforcement Learning for Imposing Policy Constraintscited by 1
  36. 2024Expert-elicitation method for non-parametric joint priors using normalizing flowscited by 1
  37. 2025Unraveling particle dark matter with Physics-Informed Neural Networkscited by 1
  38. 2025A New Stochastic Approximation Method for Gradient-based Simulated Parameter Estimationcited by 1

50 most cited of 84 All 84 (JSON)