AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

Online Conformal Prediction with Adversarial Feedback via Regret Minimization

Junyoung Yang, Kyungmin Kim, Sangdon Park

ICLR 2026 · Bandits and online learning › Online convex optimization and games · approach: Online learning with feedback graphs

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use OCP-Unlock+ (semi-bandit feedback, exploits unlocked labels) instead of full-feedback MVP oracleOCP-Unlock+ · ImageNet, i.i.d. and non-i.i.d. (alpha=0.15)miscoverage and inefficiencyNo clear effect
use OCP-Unlock+ instead of SPS under non-i.i.d. streamOCP-Unlock+ · ImageNet non-i.i.d.long-run miscoverageImproved
OCP-Unlock+ vs MVP on Airfoil regressionOCP-Unlock+ · Airfoil Self-Noise (i.i.d. and covariate shift)inefficiencyHurt
use OCP-Unlock+ instead of SPS under covariate shiftOCP-Unlock+ · Airfoil Self-Noise covariate shiftmiscoverage reliabilityImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy