paper
Optimal Deterministic Multicalibration and Omniprediction
paperactiveprovisional
optimal-deterministic-multicalibration-and-omniprediction-7d7b4bf9·1 events·first seen 47h agoAliases: Optimal Deterministic Multicalibration and Omniprediction
Co-occurring entities
More like this (12)
multicalibrationUncertainty CalibrationHuman-AI Teaming Through the Lens of CalibrationExpected Calibration Errordistributed optimizationToward Calibrated Mixture-of-Experts Under Distribution ShiftConformal PredictionMultimodal Continual Instruction TuningCalibrated SurpriseAA-OmniscienceMondrian Conformal Predictionmodel calibration
Recent events (1)
Optimal deterministic multicalibration achieved, resolving open problem on randomization necessity
A new arXiv preprint resolves an open problem in multicalibration theory by constructing a minimax-optimal multicalibration algorithm that outputs a deterministic predictor, achieving the same O(ε⁻³) sample complexity previously only attainable by randomized predictors. The result extends to outcome indistinguishability, deterministic omnipredictors, and panpredictors with optimal sample complexity, resolving multiple open problems from recent works. Multicalibration is a fairness and reliability property requiring calibration to hold across reweighted subgroups, making this relevant to trustworthy ML research.