Online Conformal Prediction with Adversarial Semi-bandit Feedback via Regret Minimization

• URL: http://arxiv.org/abs/2604.17984v1
• Date: Mon, 20 Apr 2026 09:07:40 GMT
• Title: Online Conformal Prediction with Adversarial Semi-bandit Feedback via Regret Minimization
• Abstract summary: Uncertainty quantification is crucial in safety-critical systems, where decisions must be made under uncertainty.<n>Online conformal prediction is a principled online uncertainty quantification method that dynamically constructs a prediction set at each time step.<n>We propose a novel learning method for online conformal prediction with partial feedback from an adaptive adversary.
• Score: 7.4627679994408735
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Uncertainty quantification is crucial in safety-critical systems, where decisions must be made under uncertainty. In particular, we consider the problem of online uncertainty quantification, where data points arrive sequentially. Online conformal prediction is a principled online uncertainty quantification method that dynamically constructs a prediction set at each time step. While existing methods for online conformal prediction provide long-run coverage guarantees without any distributional assumptions, they typically assume a full feedback setting in which the true label is always observed. In this paper, we propose a novel learning method for online conformal prediction with partial feedback from an adaptive adversary-a more challenging setup where the true label is revealed only when it lies inside the constructed prediction set. Specifically, we formulate online conformal prediction as an adversarial bandit problem by treating each candidate prediction set as an arm. Building on an existing algorithm for adversarial bandits, our method achieves a long-run coverage guarantee by explicitly establishing its connection to the regret of the learner. Finally, we empirically demonstrate the effectiveness of our method in both independent and identically distributed (i.i.d.) and non-i.i.d. settings, showing that it successfully controls the miscoverage rate while maintaining a reasonable size of the prediction set.

Related papers

• Online Conformal Prediction: Enforcing monotonicity via Online Optimization [23.99156538891498]
  We propose two novel online conformal prediction methods that output emphnested prediction sets across a range of coverage levels.<n>Our approaches leverage an online optimization perspective with small regret that translates to quantile estimation error control while enforcing nestedness of prediction sets.
  arXiv  Detail & Related papers  (2026-05-12T19:18:43Z)
• Distribution-informed Online Conformal Prediction [53.674678995825666]
  We propose Conformal Optimistic Prediction (COP), an online conformal prediction algorithm incorporating underlying data pattern into the update rule.<n>COP produces tighter prediction sets when predictable pattern exists, while retaining valid coverage guarantees even when estimates are inaccurate.<n>We prove that COP can achieve valid coverage and construct shorter prediction intervals than other baselines.
  arXiv  Detail & Related papers  (2025-12-08T17:51:49Z)
• SConU: Selective Conformal Uncertainty in Large Language Models [59.25881667640868]
  We propose a novel approach termed Selective Conformal Uncertainty (SConU)<n>We develop two conformal p-values that are instrumental in determining whether a given sample deviates from the uncertainty distribution of the calibration set at a specific manageable risk level.<n>Our approach not only facilitates rigorous management of miscoverage rates across both single-domain and interdisciplinary contexts, but also enhances the efficiency of predictions.
  arXiv  Detail & Related papers  (2025-04-19T03:01:45Z)
• Online Conformal Probabilistic Numerics via Adaptive Edge-Cloud Offloading [52.499838151272016]
  This work introduces a new method to calibrate the HPD sets produced by PLS with the aim of guaranteeing long-term coverage requirements.<n>The proposed method, referred to as online conformal prediction-PLS (OCP-PLS), assumes sporadic feedback from cloud to edge.<n>The validity of OCP-PLS is verified via experiments that bring insights into trade-offs between coverage, prediction set size, and cloud usage.
  arXiv  Detail & Related papers  (2025-03-18T17:30:26Z)
• Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning [53.42244686183879]
  Conformal prediction provides model-agnostic and distribution-free uncertainty quantification.<n>Yet, conformal prediction is not reliable under poisoning attacks where adversaries manipulate both training and calibration data.<n>We propose reliable prediction sets (RPS): the first efficient method for constructing conformal prediction sets with provable reliability guarantees under poisoning.
  arXiv  Detail & Related papers  (2024-10-13T15:37:11Z)
• Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback [26.87212135255959]
  In interactive imitation learning (IL), uncertainty quantification offers a way for the learner (i.e. robot) to contend with distribution shifts encountered during deployment.<n>We develop ConformalDAgger, a new approach wherein the robot uses prediction intervals calibrated by IQT as a reliable measure of deployment-time uncertainty.<n>We find that in simulated and hardware deployments on a 7DOF robotic manipulator, ConformalDAgger detects high uncertainty when the expert shifts.
  arXiv  Detail & Related papers  (2024-10-11T14:27:56Z)
• Online scalable Gaussian processes with conformal prediction for guaranteed coverage [32.21093722162573]
  The consistency of the resulting uncertainty values hinges on the premise that the learning function conforms to the properties specified by the GP model. We propose to wed the GP with the prevailing conformal prediction (CP), a distribution-free post-processing framework that produces it prediction sets with a provably valid coverage.
  arXiv  Detail & Related papers  (2024-10-07T19:22:15Z)
• Robust Conformal Prediction Using Privileged Information [17.886554223172517]
  We develop a method to generate prediction sets with a guaranteed coverage rate that is robust to corruptions in the training data.<n>Our approach builds on conformal prediction, a powerful framework to construct prediction sets that are valid under the i.i.d assumption.
  arXiv  Detail & Related papers  (2024-06-08T08:56:47Z)
• Improved Online Conformal Prediction via Strongly Adaptive Online Learning [86.4346936885507]
  We develop new online conformal prediction methods that minimize the strongly adaptive regret. We prove that our methods achieve near-optimal strongly adaptive regret for all interval lengths simultaneously. Experiments show that our methods consistently obtain better coverage and smaller prediction sets than existing methods on real-world tasks.
  arXiv  Detail & Related papers  (2023-02-15T18:59:30Z)
• Conformal Off-Policy Prediction in Contextual Bandits [54.67508891852636]
  Conformal off-policy prediction can output reliable predictive intervals for the outcome under a new target policy. We provide theoretical finite-sample guarantees without making any additional assumptions beyond the standard contextual bandit setup.
  arXiv  Detail & Related papers  (2022-06-09T10:39:33Z)
• Private Prediction Sets [72.75711776601973]
  Machine learning systems need reliable uncertainty quantification and protection of individuals' privacy. We present a framework that treats these two desiderata jointly. We evaluate the method on large-scale computer vision datasets.
  arXiv  Detail & Related papers  (2021-02-11T18:59:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.