On the Optimality of Conditional Expectation as a Bregman Predictor

DOI10.1109/TIT.2005.850145zbMath1284.94025MaRDI QIDQ3546529

Arindam Banerjee, Hui Wang, Xin Guo

Publication date: 21 December 2008

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Detection theory in information and communication theory (94A13)

Related Items (39)

Robust Bregman clustering ⋮ Regular conditional probabilities and strictly proper loss functions ⋮ Forecast dominance testing via sign randomization ⋮ The information geometry of Bregman divergences and some applications in multi-expert reasoning ⋮ A column-wise update algorithm for nonnegative matrix factorization in Bregman divergence with an orthogonal constraint ⋮ Optimal estimation of the supremum and occupation times of a self-similar Lévy process ⋮ Linear scoring rules for probabilistic binary classification ⋮ Higher order elicitability and Osband's principle ⋮ Prediction in Riemannian metrics derived from divergence functions ⋮ Certified dimension reduction in nonlinear Bayesian inverse problems ⋮ On Bayesian estimation and proximity operators ⋮ Rational inattention when decisions take time ⋮ On Testing Equal Conditional Predictive Ability Under Measurement Error ⋮ A \(k\)-points-based distance for robust geometric inference ⋮ Re-examination of Bregman functions and new properties of their divergences ⋮ Cost-sensitive learning based on Bregman divergences ⋮ Kullback-Leibler average, consensus on probability densities, and distributed state estimation with guaranteed stability ⋮ Parametric Bayesian estimation of differential entropy and relative entropy ⋮ Income distributions and decomposable divergence measures ⋮ A Partitioning Deletion/Substitution/Addition Algorithm for Creating Survival Risk Groups ⋮ Calibration and regret bounds for order-preserving surrogate losses in learning to rank ⋮ Aggregation functions based on penalties ⋮ Convergence rates for the generalized Fréchet mean via the quadruple inequality ⋮ Unnamed Item ⋮ An improved Bregman \(k\)-means++ algorithm via local search ⋮ Quantization and clustering with Bregman divergences ⋮ Axiomatic generalization of the membership degree weighting function for fuzzy \(C\) means clustering: theoretical development and convergence analysis ⋮ Bregman divergences in the \((m\times k)\)-partitioning problem ⋮ On Bayesian posterior mean estimators in imaging sciences and Hamilton-Jacobi partial differential equations ⋮ Aggregating incoherent agents who disagree ⋮ History-Independent Distributed Multi-agent Learning ⋮ New aspects of Bregman divergence in regression and classification with parametric and nonparametric estimation ⋮ KFC: A clusterwise supervised learning procedure based on the aggregation of distances ⋮ Low-Rank Approximation and Completion of Positive Tensors ⋮ Solving inverse problems using data-driven models ⋮ Improved local search algorithms for Bregman \(k\)-means and its variants ⋮ Practical Bayesian tomography ⋮ A Spectral Estimation Framework for Phase Retrieval via Bregman Divergence Minimization ⋮ Elicitable distortion risk measures: a concise proof

This page was built for publication: On the Optimality of Conditional Expectation as a Bregman Predictor