mlsanityData to 14 Oct 2026

Statistical applications of contrastive learning

arXiv 2204.13999 ↗First posted 29 Apr 2022cs.LG stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

The likelihood function plays a crucial role in statistical inference and experimental design. However, it is computationally intractable for several important classes of statistical models, including energy-based models and simulator-based models. Contrastive learning is an intuitive and computationally feasible alternative to likelihood-based learning. We here first provide an introduction to contrastive learning and then show how we can use it to derive methods for diverse statistical problems, namely parameter estimation for energy-based models, Bayesian inference for simulator-based models, as well as experimental design.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 35 of its 77 references that are in the map. First posted on arXiv 29 Apr 2022.

Builds on

35 of 77 references.

References · 35

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  4. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  5. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  6. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  7. 2019On Variational Bounds of Mutual Informationcited by 559
  8. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  9. 2019The frontier of simulation-based inferencecited by 502
  10. 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 384
  11. 2021How to Train Your Energy-Based Modelscited by 274
  12. 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 273
23 more
  1. 2016Learning in Implicit Generative Modelscited by 125
  2. 2019Variational Bayesian Optimal Experimental Designcited by 116
  3. 2020Telescoping Density-Ratio Estimationcited by 108
  4. 2020On Contrastive Learning for Likelihood-free Inferencecited by 98
  5. 2021Oops I Took A Gradient: Scalable Sampling for Discrete Distributionscited by 92
  6. 2019A Mutual Information Maximization Perspective of Language Representation Learningcited by 85
  7. 2016Likelihood-free inference by ratio estimationcited by 81
  8. 2019Flow Contrastive Estimation of Energy-Based Modelscited by 75
  9. 2020Neural Approximate Sufficient Statistics for Implicit Modelscited by 74
  10. 2020A Contrastive Learning Approach for Training Variational Autoencoder Priorscited by 66
  11. 2021Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoodscited by 61
  12. 2021Density Ratio Estimation via Infinitesimal Classificationcited by 61
  13. 2019A Unified Stochastic Gradient Approach to Designing Bayesian-Optimal Experimentscited by 58
  14. 2020Bayesian Experimental Design for Implicit Models by Mutual Information Neural Estimationcited by 56
  15. 2018Efficient Bayesian Experimental Design for Implicit Modelscited by 34
  16. 2021Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Boundscited by 27
  17. 2018Conditional Noise-Contrastive Estimation of Unnormalised Modelscited by 25
  18. 2020Sequential Bayesian Experimental Design for Implicit Models via Mutual Informationcited by 23
  19. 2014On distinguishability criteria for estimating generative modelscited by 21
  20. 2021Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimationcited by 15
  21. 2014Likelihood-free inference via classificationcited by 13
  22. 2018Dynamic Likelihood-free Inference via Ratio Estimation (DIRE)cited by 7
  23. 2018Variational Noise-Contrastive Estimationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 0; 2026: 1.

5 papers.

  1. 2022Contrastive Neural Ratio Estimation for Simulation-based Inferencecited by 7
  2. 2023Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive Estimationcited by 2
  3. 2023A Simplified Framework for Contrastive Learning for Node Representationscited by 1
  4. 2024SoftCVI: Contrastive variational inference with self-generated soft labelscited by 1
  5. 2026A unifying view of contrastive learning, importance sampling, and bridge sampling for energy-based modelscited by 0