mlsanityData to 13 Oct 2026

Online Conformal Prediction with Corrupted Feedback

arXiv 2605.20515 ↗First posted 19 May 2026cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Online conformal prediction (OCP) addresses this challenge through adaptively updated prediction sets that provide deterministic long-run miscoverage guarantees. These guarantees, however, hinge on the assumption of perfect feedback about the coverage of past prediction sets. In practice, the observed miscoverage indicator may be corrupted by noise, communication failures, or adversarial manipulation, which can severely degrade OCP's calibration guarantees. In this paper, we study OCP under corrupted feedback. We first model feedback corruption as an arbitrary binary flip sequence, and analyze how feedback corruption affects and degrades the miscoverage performance of standard OCP. We then propose two robust schemes: robust OCP via filtering, which leverages the structural properties of the predicted threshold to filter corrupted feedback, and robust OCP via active compensation, which incorporates an active compensation mechanism to mitigate the effect of corrupted feedback. For both methods, we establish explicit miscoverage guarantees, which are further specialized for an independent stochastic flip model and for an arbitrary error model with memory bounds. Experiments on real-world datasets validate the proposed approach, showing markedly improved calibration and significantly smaller prediction sets compared with baseline OCP methods under corrupted feedback.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

32 of 44 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 817
  3. 2021A Survey of Uncertainty in Deep Neural Networkscited by 676
  4. 2019Online Learning: A Modern Introduction Using Convex Optimizationcited by 412
  5. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 367
  6. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 365
  7. 2022Conformal Inference for Online Prediction with Arbitrary Distribution Shiftscited by 125
  8. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 119
  9. 2023Improved Online Conformal Prediction via Strongly Adaptive Online Learningcited by 77
  10. 2018Exact and Robust Conformal Inference Methods for Predictive Machine Learning With Dependent Datacited by 65
  11. 2024Online conformal prediction with decaying step sizescited by 55
  12. 2020Conformal prediction for time seriescited by 53
20 more
  1. 2024JUICER: Data-Efficient Imitation Learning for Robotic Assemblycited by 36
  2. 2022Parameter-free Regret in High Probability with Heavy Tailscited by 27
  3. 2022Label Noise Robustness of Conformal Predictioncited by 20
  4. 2024Localized Adaptive Risk Controlcited by 16
  5. 2025Gradient Equilibrium in Online Learning: Theory and Applicationscited by 13
  6. 2025Error-quantified Conformal Inference for Time Seriescited by 11
  7. 2025Conformal Calibration: Ensuring the Reliability of Black-Box AI in Wireless Systemscited by 11
  8. 2023Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filtercited by 10
  9. 2025Mirror Online Conformal Prediction with Intermittent Feedbackcited by 7
  10. 2024Conformal Distributed Remote Inference in Sensor Networks Under Reliability and Communication Constraintscited by 5
  11. 2025Conformal Inference for Time Series over Graphscited by 5
  12. 2021Robust Online Convex Optimization in the Presence of Outlierscited by 4
  13. 2025Exploring the Noise Robustness of Online Conformal Predictioncited by 4
  14. 2025Remote Inference over Dynamic Links via Adaptive Rate Deep Task-Oriented Vector Quantizationcited by 3
  15. 2025Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weightingcited by 3
  16. 2025Unconstrained Robust Online Convex Optimizationcited by 3
  17. 2018Secure Mobile Edge Computing in IoT via Collaborative Online Learningcited by 2
  18. 2025KPI Poisoning: An Attack in Open RAN Near Real-Time Control Loopcited by 2
  19. 2025Prediction-Powered Communication with Distortion Guaranteescited by 2
  20. 2025Distribution-informed Online Conformal Predictioncited by 2

Built on by

Not cited yet.