mlsanityData to 7 Oct 2026

Calibrating AI Models for Wireless Communications via Conformal Prediction

arXiv 2212.07775 ↗First posted 15 Dec 2022cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

When used in complex engineered systems, such as communication networks, artificial intelligence (AI) models should be not only as accurate as possible, but also well calibrated. A well-calibrated AI model is one that can reliably quantify the uncertainty of its decisions, assigning high confidence levels to decisions that are likely to be correct and low confidence levels to decisions that are likely to be erroneous. This paper investigates the application of conformal prediction as a general framework to obtain AI models that produce decisions with formal calibration guarantees. Conformal prediction transforms probabilistic predictors into set predictors that are guaranteed to contain the correct answer with a probability chosen by the designer. Such formal calibration guarantees hold irrespective of the true, unknown, distribution underlying the generation of the variables of interest, and can be defined in terms of ensemble or time-averaged probabilities. In this paper, conformal prediction is applied for the first time to the design of AI for communication systems in conjunction to both frequentist and Bayesian learning, focusing on demodulation, modulation classification, and channel prediction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 46 of its 108 references that are in the map. First posted on arXiv 15 Dec 2022.

Builds on

46 of 108 references.

References · 46

  1. 2017On Calibration of Modern Neural Networkscited by 4,860
  2. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  3. 2016Distribution-Free Predictive Inference For Regressioncited by 657
  4. 2019Conformal Prediction Under Covariate Shiftcited by 511
  5. 2020Classification with Valid and Adaptive Coveragecited by 390
  6. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 360
  7. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  8. 2022Conformal prediction beyond exchangeabilitycited by 348
  9. 2019Verified Uncertainty Calibrationcited by 307
  10. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  11. 2019Predictive inference with the jackknife+cited by 206
  12. 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
34 more
  1. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
  2. 2019Evaluating model calibration in classificationcited by 165
  3. 2022Adaptive Conformal Predictions for Time Seriescited by 155
  4. 2017Over the Air Deep Learning Based Radio Signal Classificationcited by 121
  5. 2020Conformal Prediction: a Unified Review of Theory and New Challengescited by 118
  6. 2021Learning Optimal Conformal Classifierscited by 108
  7. 2016Convolutional Radio Modulation Recognition Networkscited by 106
  8. 2022Training Uncertainty-Aware Classifiers with Conformalized Deep Learningcited by 62
  9. 2022Probabilistic Conformal Prediction Using Conditional Random Samplescited by 47
  10. 2022Investigating the Impact of Model Misspecification in Neural Simulation-based Inferencecited by 44
  11. 2020Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptationcited by 43
  12. 2018Communication Algorithms via Deep Learningcited by 42
  13. 2020Deep Learning for Wireless Communicationscited by 39
  14. 2022Achieving Risk Control in Online Learning Settingscited by 38
  15. 2018A Very Brief Introduction to Machine Learning With Applications to Communication Systemscited by 35
  16. 2021Meta-Cal: Well-controlled Post-hoc Calibration by Rankingcited by 33
  17. 2022Beyond calibration: estimating the grouping loss of modern neural networkscited by 32
  18. 2022Conformal Prediction with Temporal Quantile Adjustmentscited by 25
  19. 2016Patterns of Scalable Bayesian Inferencecited by 24
  20. 2019Learning to Demodulate from Few Pilots via Offline and Online Meta-Learningcited by 21
  21. 2020Deep Learning for Wireless Communications: An Emerging Interdisciplinary Paradigmcited by 20
  22. 2022Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal Predictioncited by 17
  23. 2022Annealed Langevin Dynamics for Massive MIMO Detectioncited by 16
  24. 2021Modular Meta-Learning for Power Control via Random Edge Graph Neural Networkscited by 13
  25. 2019MIND: Model Independent Neural Decodercited by 11
  26. 2022Robust Bayesian Learning for Reliable Wireless AI: Framework and Applicationscited by 9
  27. 2020Making learning more transparent using conformalized performance predictioncited by 8
  28. 2017Langevin Dynamics with Continuous Tempering for Training Deep Neural Networkscited by 7
  29. 2021Model-Based Machine Learning for Communicationscited by 7
  30. 2022Robust PACm: Training Ensemble Models Under Misspecification and Outlierscited by 6
  31. 2015Millimeter Wave Cellular Networks: A MAC Layer Perspectivecited by 3
  32. 2022AI-Based Channel Prediction in D2D Links: An Empirical Validationcited by 3
  33. 2017Probably approximate Bayesian computation: nonasymptotic convergence of ABC under misspecificationcited by 2
  34. 2021Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalizationcited by 2

Built on by

Not cited yet.