Optimal Recalibration of an Online Predictor

arXiv:2607.19689 · stat.ML, cs.DS, cs.LG · Submitted 2026-07-22 · Read on arXiv

Lunjia Hu, Kevin Tian, Chutong Yang

stat.ML, cs.DS, cs.LG

Submitted: 2026-07-22

Code: https://github.com/chutongyang98/Optimal-Recalibration-of-an-Online-Predictor

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 91× in this paper · explained in 9 episodes
• Regret — 21× in this paper · explained in 4 episodes
• Sparsity — 8× in this paper · explained in 5 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Generalization — 5× in this paper · explained in 14 episodes
• Distribution Shift — 3× in this paper · explained in 12 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Regret Bound — 2× in this paper · explained in 2 episodes
• Weight Decay — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 3 episodes
• Concept Drift — 1× in this paper · explained in 6 episodes
• Confidence Calibration — 1× in this paper · explained in 2 episodes
• Editor — 1× in this paper · explained in 2 episodes
• Hilbert Space — 1× in this paper · explained in 2 episodes
• Hyperparameters — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Minimax Optimality — 1× in this paper · explained in 3 episodes
• Monotonicity — 1× in this paper · explained in 2 episodes
• Parameterization — 1× in this paper · explained in 2 episodes
• Regret Bounds — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes

Sources

• Calibeating Made Simple
• Optimal Lower Bounds for Online Multicalibration
• Proper Calibeating
• Efficient Swap Multicalibration of Elicitable Properties
• Simultaneous Blackwell Approachability and Applications to Multiclass Omniprediction
• Language Models (Mostly) Know What They Know
• Improved Bounds for Swap Multicalibration and Swap Omniprediction
• Near-Optimal Algorithms for Omniprediction

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Scalable Posterior Uncertainty for Flexible Density-Based Clustering
• A Transport Geometry of Benign Overfitting
• Efficient quadratic entropy with distance sketches