mlsanityData to 7 Oct 2026

Rao-Blackwellized Stochastic Gradients for Discrete Distributions

arXiv 1810.04777 ↗First posted 10 Oct 2018stat.ML cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

We wish to compute the gradient of an expectation over a finite or countably infinite sample space having K ≤ ∞ categories. When K is indeed infinite, or finite but very large, the relevant summation is intractable. Accordingly, various stochastic gradient estimators have been proposed. In this paper, we describe a technique that can be applied to reduce the variance of any such estimator, without changing its bias---in particular, unbiasedness is retained. We show that our technique is an instance of Rao-Blackwellization, and we demonstrate the improvement it yields on a semi-supervised classification problem and a pixel attention task.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 4; 2023: 2; 2024: 1; 2025: 2; 2026: 5.

23 papers.

Sort:

By area:

  1. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  2. 2021Implicit MLE: Backpropagating Through Discrete Exponential Family Distributionscited by 97
  3. 2023A Survey on Fairness in Large Language Modelscited by 91
  4. 2023Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trickcited by 13
  5. 2022Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Modelscited by 12
  6. 2021Storchastic: A Framework for General Stochastic Automatic Differentiationcited by 11
  7. 2021Conditional Poisson Stochastic Beam Searchcited by 11
  8. 2021Coupled Gradient Estimators for Discrete Latent Variablescited by 9
  9. 2021Fast and Scalable Spike and Slab Variable Selection in High-Dimensional Gaussian Processescited by 7
  10. 2022Hierarchical Phrase-based Sequence-to-Sequence Learningcited by 7
  11. 2021Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Modelscited by 6
  12. 2024On Divergence Measures for Training GFlowNetscited by 6
11 more
  1. 2022Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networkscited by 5
  2. 2021CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimatorcited by 4
  3. 2021Scaling Structured Inference with Randomizationcited by 2
  4. 2021Coordinate-wise Control Variates for Deep Policy Gradientscited by 1
  5. 2025Rao-Blackwellised Reparameterisation Gradientscited by 1
  6. 2025Beyond Softmax: A Natural Parameterization for Categorical Random Variablescited by 0
  7. 2026Categorical Reparameterization with Denoising Diffusion modelscited by 0
  8. 2026The Theorems of Dr. David Blackwell and Their Contributions to Artificial Intelligencecited by 0
  9. 2026TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learningcited by 0
  10. 2026GradInf: Gradient Estimation as Probabilistic Inferencecited by 0
  11. 2026Accelerating Evolutionary Strategy via Rao-Blackwellizing Realization of Uncertain Inputcited by 0