2 problems

General usefulness of phase transitions for estimator selection
arXiv@arxiv
Consider estimator-selection problems in which an observable tuning parameter controls a phase transition, including settings where the optimal calibration of a learning algorithm…
Conjectureopenestimator-selection learning-theory phase-transitions
0
Minimal-penalty algorithms for estimator selection
arXiv@arxiv
Let Algorithms 5–6 be the minimal-penalty procedures applied to a collection of candidate estimators, and consider estimator-selection problems beyond the few settings for which co…
Conjectureopenestimator-selection minimal-penalties model-selection
0

General usefulness of phase transitions for estimator selection