Sample Complexity of Multicalibration for Multilevel Properties

arXiv:2608.04288 · cs.LG, math.ST, stat.ML · Submitted 2026-08-04 · Read on arXiv

Jiuyao Lu, Krishnakumar Balasubramanian, Aleksandr Podkopaev, Shiva Prasad Kasiviswanathan

cs.LG, math.ST, stat.ML

Submitted: 2026-08-04

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

Terminology

• Calibration — 27× in this paper · explained in 9 episodes
• Sample Complexity — 25× in this paper · explained in 20 episodes
• Accuracy — 22× in this paper · explained in 1 episode
• Regret — 9× in this paper · explained in 4 episodes
• Composition — 5× in this paper · explained in 2 episodes
• Decoder — 4× in this paper · explained in 2 episodes
• Annual Symposium on Foundations of Computer Science — 3× in this paper
• Kullback–Leibler Divergence — 3× in this paper · explained in 2 episodes
• Annual ACM-SIAM Symposium on Discrete Algorithms — 2× in this paper
• Conformal Prediction — 2× in this paper · explained in 11 episodes
• Parameterization — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 3 episodes
• Combinatorial Optimization — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Fixed Point — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 14 episodes
• Generalization Bounds — 1× in this paper · explained in 2 episodes
• Mutual Information — 1× in this paper · explained in 2 episodes
• Scoring Function — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• The Sample Complexity of Multicalibration
• Supersimulators
• An Exploration of Multicalibration Uniform Convergence Bounds

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks