mlsanityData to 7 Oct 2026

Meta-learning Control Variates: Variance Reduction with Limited Data

arXiv 2303.04756 ↗First posted 8 Mar 2023stat.ME cs.LG stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

Control variates can be a powerful tool to reduce the variance of Monte Carlo estimators, but constructing effective control variates can be challenging when the number of samples is small. In this paper, we show that when a large number of related integrals need to be computed, it is possible to leverage the similarity between these integration tasks to improve performance even when the number of samples per task is very small. Our approach, called meta learning CVs (Meta-CVs), can be used for up to hundreds or thousands of tasks. Our empirical assessment indicates that Meta-CVs can lead to significant variance reduction in such settings, and our theoretical analysis establishes general conditions under which Meta-CVs can be successfully trained.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 36 of its 71 references that are in the map. First posted on arXiv 8 Mar 2023.

Builds on

36 of 71 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2021Convex optimizationcited by 2,479
  5. 2016Learning to learn by gradient descent by gradient descentcited by 616
  6. 2018How to train your MAMLcited by 306
  7. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  8. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  9. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  10. 2016Automatic Differentiation Variational Inferencecited by 159
  11. 2018Survey of multifidelity methods in uncertainty propagation, inference, and optimizationcited by 141
  12. 2019Online Meta-Learningcited by 137
24 more
  1. 2019On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithmscited by 132
  2. 2017Backpropagation through the Void: Optimizing control variates for black-box gradient estimationcited by 104
  3. 2019Generalized Inner Loop Meta-Learningcited by 92
  4. 2014Control functionals for Monte Carlo integrationcited by 59
  5. 2021Generalization Bounds For Meta-Learning: An Information-Theoretic Analysiscited by 45
  6. 2020Neural Control Variatescited by 34
  7. 2021Stein's Method Meets Computational Statistics: A Review of Some Recent Developmentscited by 32
  8. 2019Approximate Inference for Fully Bayesian Gaussian Process Regressioncited by 31
  9. 2017Control Variates for Stochastic Gradient MCMCcited by 25
  10. 2022Gradient Estimation with Discrete Stein Operatorscited by 22
  11. 2019Active Multi-Information Source Bayesian Quadraturecited by 17
  12. 2018Bayesian Quadrature for Multiple Related Integralscited by 15
  13. 2021Vector-Valued Control Variatescited by 12
  14. 2018Regularized Zero-Variance Control Variatescited by 10
  15. 2020Scalable Control Variates for Monte Carlo Methods via Stochastic Optimizationcited by 10
  16. 2020Semi-Exact Control Functionals From Sard's Methodcited by 9
  17. 2022Multilevel Bayesian Quadraturecited by 8
  18. 2023Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayescited by 8
  19. 2021Post-Processing of MCMCcited by 5
  20. 2022Efficient estimation of multiple expectations with the same sample by adaptive importance sampling and control variatescited by 3
  21. 2014The Controlled Thermodynamic Integral for Bayesian Model Comparisoncited by 2
  22. 2018Neural Control Variates for Variance Reductioncited by 2
  23. 2019Variance reduction for Markov chains with application to MCMCcited by 2
  24. 2022Variance Reduction for Metropolis-Hastings Samplerscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 1; 2026: 2.

6 papers.

  1. 2024Conditional Bayesian Quadraturecited by 8
  2. 2023Theoretical guarantees for neural control variates in MCMCcited by 4
  3. 2023Bayesian Numerical Integration with Neural Networkscited by 3
  4. 2026Conditional neural control variates for variance reduction in Bayesian inverse problemscited by 2
  5. 2025Training neural control variates using correlated configurationscited by 1
  6. 2026Amortized quadrature for posterior expectations in inverse problemscited by 0