A Bregman divergence approach yields a general calibeating framework that achieves U-calibration with logarithmic regret for Tsallis losses and a new regret equality for Be The Regularized Leader.
Annals of the Institute of Statistical Mathematics , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Temperature scaling of density-matrix eigenvalues from LLM semantic embeddings optimizes proper-score calibration and corrects systematic overconfidence so entropy equals risk.
Predictive Bayesian inference posteriors concentrate onto a forward-model-dependent quantity and produce miscalibrated credible sets unless the predictive model contains the true data-generating process.
citing papers explorer
-
Calibeating for general proper losses: A Bregman divergence approach
A Bregman divergence approach yields a general calibeating framework that achieves U-calibration with logarithmic regret for Tsallis losses and a new regret equality for Be The Regularized Leader.
-
Eigenvalue Calibration for Semantic Embeddings of Large Language Models
Temperature scaling of density-matrix eigenvalues from LLM semantic embeddings optimizes proper-score calibration and corrects systematic overconfidence so entropy equals risk.
-
Concentration and Calibration in Predictive Bayesian Inference
Predictive Bayesian inference posteriors concentrate onto a forward-model-dependent quantity and produce miscalibrated credible sets unless the predictive model contains the true data-generating process.