Information, Divergence and Risk for Binary Experiments

zbMath1280.68192arXiv0901.0356MaRDI QIDQ5396625

Mark D. Reid, Robert C. Williamson

Publication date: 3 February 2014

Full work available at URL: https://arxiv.org/abs/0901.0356

zbMATH Keywords

classificationdivergenceregret boundsloss functionsstatistical information

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Surrogate regret bounds for generalized classification performance metrics ⋮ Unnamed Item ⋮ The Bregman Proximal Average ⋮ Calibrating sufficiently ⋮ A Proximal Average for Prox-Bounded Functions ⋮ A historical perspective on Schützenberger-Pinsker inequalities ⋮ Calibrated asymmetric surrogate losses ⋮ Minimax optimal sequential hypothesis tests for Markov processes ⋮ Divergence for \(s\)-concave and log concave functions ⋮ Support vector machines based on convex risk functions and general norms ⋮ Multiclass classification, information, divergence and surrogate risk ⋮ Mixedf-divergence and inequalities for log-concave functions ⋮ Unnamed Item ⋮ A Steiner formula in the \(L_p\) Brunn Minkowski theory ⋮ Forecaster's dilemma: extreme events and forecast evaluation ⋮ Some Universal Insights on Divergences for Statistics, Machine Learning and Artificial Intelligence ⋮ Generalized twin Gaussian processes using Sharma-Mittal divergence ⋮ A Spectral Estimation Framework for Phase Retrieval via Bregman Divergence Minimization

Uses Software

• HandTill2001

This page was built for publication: Information, Divergence and Risk for Binary Experiments