mlsanityData to 7 Oct 2026

Joint control variate for faster black-box variational inference

arXiv 2210.07290 ↗First posted 13 Oct 2022cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Black-box variational inference performance is sometimes hindered by the use of gradient estimators with high variance. This variance comes from two sources of randomness: Data subsampling and Monte Carlo sampling. While existing control variates only address Monte Carlo noise, and incremental gradient methods typically only address data subsampling, we propose a new "joint" control variate that jointly reduces variance from both sources of noise. This significantly reduces gradient variance, leading to faster optimization in several applications.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 40 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

20 of 40 references.

References · 20

  1. 2016Variational Inference: A Review for Statisticianscited by 1,466
  2. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  3. 2014SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectivescited by 401
  4. 2013Black Box Variational Inferencecited by 317
  5. 2019Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyrocited by 187
  6. 2016Automatic Differentiation Variational Inferencecited by 159
  7. 2017Doubly Stochastic Variational Inference for Deep Gaussian Processescited by 143
  8. 2017Backpropagation through the Void: Optimizing control variates for black-box gradient estimationcited by 104
  9. 2017Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inferencecited by 97
  10. 2020Variance-Reduced Methods for Machine Learningcited by 79
  11. 2017REBAR: Low-variance, unbiased gradient estimates for discrete latent variable modelscited by 78
  12. 2018Variance reduction properties of the reparameterization trickcited by 41
8 more
  1. 2014Incremental Majorization-Minimization Optimization with Application to Large-Scale Machine Learningcited by 35
  2. 2017Reducing Reparameterization Gradient Variancecited by 27
  3. 2018Using Large Ensembles of Control Variates for Variational Inferencecited by 21
  4. 2014Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problemscited by 10
  5. 2020Approximation Based Variance Reduction for Reparameterization Gradientscited by 10
  6. 2016Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structurecited by 8
  7. 2020Amortized variance reduction for doubly stochastic objectivescited by 3
  8. 2018Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Datacited by 2

Built on by

Not cited yet.