Optimal Deterministic Multicalibration and Omniprediction
Georgy Noarov, Aaron Roth
cs.LG, math.ST, stat.ML
Submitted: 2026-06-18
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Panprediction: Optimal Predictions for Any Downstream Task and Loss
- Optimal Lower Bounds for Online Multicalibration
- The Sample Complexity of Multicalibration
- Supersimulators
- Derandomizing Multi-Distribution Learning
- 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