mlsanityData to 7 Oct 2026

Mirror Online Conformal Prediction with Intermittent Feedback

arXiv 2503.10345 ↗First posted 13 Mar 2025cs.LG eess.SPcited by 6

Not on the map. Why?

Abstract (arXiv)

Online conformal prediction enables the runtime calibration of a pre-trained artificial intelligence model using feedback on its performance. Calibration is achieved through set predictions that are updated via online rules so as to ensure long-term coverage guarantees. While recent research has demonstrated the benefits of incorporating prior knowledge into the calibration process, this has come at the cost of replacing coverage guarantees with less tangible regret guarantees based on the quantile loss. This work introduces intermittent mirror online conformal prediction (IM-OCP), a novel runtime calibration framework that integrates prior knowledge, operates under potentially intermittent feedback, and features minimal memory complexity. IM-OCP guarantees long-term coverage and sub-linear regret, both of which hold deterministically for any given data sequence and in expectation with respect to the intermittent feedback.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 31 references that are in the map. First posted on arXiv 13 Mar 2025.

Builds on

19 of 31 references.

References · 19

  1. 2019Introduction to Online Convex Optimizationcited by 793
  2. 2019Online Learning: A Modern Introduction Using Convex Optimizationcited by 407
  3. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 360
  4. 2022Safe Planning in Dynamic Environments using Conformal Predictioncited by 112
  5. 2024Large language model validity via enhanced conformal prediction methodscited by 91
  6. 2023Conformal PID Control for Time Series Predictioncited by 85
  7. 2023Improved Online Conformal Prediction via Strongly Adaptive Online Learningcited by 76
  8. 2021Fair Conformal Predictors for Applications in Medical Imagingcited by 74
  9. 2024Online conformal prediction with decaying step sizescited by 53
  10. 2022Achieving Risk Control in Online Learning Settingscited by 38
  11. 2020On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regressioncited by 33
  12. 2023Forking Uncertainties: Reliable Prediction and Model Predictive Control with Sequence Models via Conformal Risk Controlcited by 19
7 more
  1. 2024Localized Adaptive Risk Controlcited by 16
  2. 2025Gradient Equilibrium in Online Learning: Theory and Applicationscited by 12
  3. 2024Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedbackcited by 11
  4. 2024Semi-Supervised Learning via Cross-Prediction-Powered Inference for Wireless Systemscited by 10
  5. 2023Guaranteed Dynamic Scheduling of Ultra-Reliable Low-Latency Traffic via Conformal Predictioncited by 5
  6. 2025Exploring the Noise Robustness of Online Conformal Predictioncited by 4
  7. 2024The Benefit of Being Bayesian in Online Conformal Predictioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Conformal Calibration: Ensuring the Reliability of Black-Box AI in Wireless Systemscited by 10
  2. 2025Distribution-informed Online Conformal Predictioncited by 2
  3. 2026Coverage Guarantees for Pseudo-Calibrated Conformal Prediction under Distribution Shiftcited by 1
  4. 2026Online Conformal Prediction for Non-Exchangeable Panel Datacited by 0
  5. 2026Online Conformal Prediction with Corrupted Feedbackcited by 0
  6. 2026Online Conformal Prediction Beyond Feedbackcited by 0