Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory

DOI10.1214/009053604000000553zbMath1048.62008arXivmath/0410076OpenAlexW1590693676WikidataQ59631784 ScholiaQ59631784MaRDI QIDQ1879959

Yanyan Li

Publication date: 15 September 2004

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/math/0410076

zbMATH Keywords

minimaxmaximinrelative entropymutual informationconvexitydualitysaddle-pointexponential familyKullback-Leibler divergencespecific entropyBregman divergencescoring ruleadditive modeluncertainty functionBrier scoreredundancy-capacity theoremPythagorean propertylogarithmic scorezero-one lossGamma-minimaxBayes actequalizer rulegeneralized exponential familymean-value constraints

Mathematics Subject Classification ID

Minimax procedures in statistical decision theory (62C20) Applications of game theory (91A80) Other game-theoretic models (91A40) Measures of information, entropy (94A17) Statistical aspects of information-theoretic topics (62B10)

Related Items (84)

Bayesian model selection based on proper scoring rules ⋮ Objective Bayesianism and the maximum entropy principle ⋮ Bayesian testing of a point null hypothesis based on the latent information prior ⋮ Group invariance of information geometry on \(q\)-Gaussian distributions induced by beta-divergence ⋮ Robust probability updating ⋮ Coherent Frequentism: A Decision Theory Based on Confidence Sets ⋮ Duality of maximum entropy and minimum divergence ⋮ Pitman closeness properties of point estimators and predictive densities with parametric constraints ⋮ Linear scoring rules for probabilistic binary classification ⋮ Generalised exponential families and associated entropy functions ⋮ Maximum entropy on compact groups ⋮ Non-extensivity of the configurational density distribution in the classical microcanonical ensemble ⋮ A triple uniqueness of the maximum entropy approach ⋮ Weighted Scoring Rules and Convex Risk Measures ⋮ Equivocation for the objective Bayesian ⋮ Notions of the ergodic hierarchy for curved statistical manifolds ⋮ Pitman closeness properties of Bayes shrinkage procedures in estimation and prediction ⋮ Exact credibility reference Bayesian premiums ⋮ Reporting Bayes factors or probabilities to decision makers of unknown loss functions ⋮ Unnamed Item ⋮ Frameworks and results in distributionally robust optimization ⋮ Unnamed Item ⋮ A simple robust asset pricing model under statistical ambiguity ⋮ Counterfactual prediction in complete information games: point prediction under partial identification ⋮ The geometry of proper scoring rules ⋮ Necessary and sufficient conditions of proper estimators based on self density ratio for unnormalized statistical models ⋮ On combinatorial rectangles with minimum ∞−discrepancy ⋮ Bayesian model diagnostics using functional Bregman divergence ⋮ Properization: constructing proper scoring rules via Bayes acts ⋮ Clinical and operational risk: a Bayesian approach ⋮ Logical perspectives on the foundations of probability ⋮ Projective power entropy and maximum Tsallis entropy distributions ⋮ Bayes risk, elicitability, and the Expected Shortfall ⋮ Maximum entropy derived and generalized under idempotent probability to address Bayes-frequentist uncertainty and model revision uncertainty: an information-theoretic semantics for possibility theory ⋮ Blending Bayesian and frequentist methods according to the precision of prior information with applications to hypothesis testing ⋮ Probabilism, entropies and strictly proper scoring rules ⋮ Inference after checking multiple Bayesian models for data conflict and applications to mitigating the influence of rejected priors ⋮ Robust estimation in regression and classification methods for large dimensional data ⋮ An information-theoretic approach to partially identified auction models ⋮ Informational separability and entropy ⋮ How uncertain do we need to be? ⋮ Unnamed Item ⋮ Controlling the degree of caution in statistical inference with the Bayesian and frequentist approaches as opposite extremes ⋮ Asymptotically minimax Bayesian predictive densities for multinomial models ⋮ Additive Scoring Rules for Discrete Sample Spaces ⋮ Invariant equivocation ⋮ A survey of Bayesian predictive methods for model assessment, selection and comparison ⋮ Entropy concentration and the empirical coding game ⋮ Game-theoretic probability combination with applications to resolving conflicts between statistical methods ⋮ Affine invariant divergences associated with proper composite scoring rules and their applications ⋮ Adaptive decision making via entropy minimization ⋮ A general framework for maximizing likelihood under incomplete data ⋮ Evaluating probability forecasts ⋮ Why frequentists and Bayesians need each other ⋮ A survey of inverse reinforcement learning: challenges, methods and progress ⋮ Unnamed Item ⋮ Multiclass classification, information, divergence and surrogate risk ⋮ Generalised entropies and asymptotic complexities of languages ⋮ Unnamed Item ⋮ Descriptive measures for nominal categorical variables ⋮ Generalized Conditional Entropy — Determinicity of a Process and Rokhlin's Formula ⋮ Game theoretical optimization inspired by information theory ⋮ Supermartingales in prediction with expert advice ⋮ Unnamed Item ⋮ Proper scoring rules with general preferences: a dual characterization of optimal reports ⋮ Robust Loss Functions for Boosting ⋮ Bayesian predictive densities based on latent information priors ⋮ Maximum entropy distributions with quantile information ⋮ Measuring exposure to dependence risk with random Bernstein copula scenarios ⋮ Game Theoretical Approach for Reliable Enhanced Indexation ⋮ Generating Spike Trains with Specified Correlation Coefficients ⋮ MEASURING DISTRIBUTION MODEL RISK ⋮ Justifying the principle of indifference ⋮ Boosting in the Presence of Outliers: Adaptive Classification With Nonconvex Loss Functions ⋮ Bregman divergences in the \((m\times k)\)-partitioning problem ⋮ Modeling the Correlated Activity of Neural Populations: A Review ⋮ Rejoinder on: Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds ⋮ New aspects of Bregman divergence in regression and classification with parametric and nonparametric estimation ⋮ Comments on: Assessing probabilistic forecasts of multivariate quantities, with an application to ensemble predictions of surface winds ⋮ Statistical file-matching of non-Gaussian data: a game theoretic approach ⋮ Conjugate predictive distributions and generalized entropies ⋮ A multiobjective hybrid ant colony optimization approach applied to the assignment and scheduling problem ⋮ Kernel density estimation based distributionally robust mean-CVaR portfolio optimization ⋮ Linear estimating equations for exponential families with application to Gaussian linear concentration models

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Can the maximum entropy principle be explained as a consistency requirement?
• The constraint rule of the maximum entropy principle
• Diversity and dissimilarity coefficients: A unified approach
• Statistical decision theory and Bayesian analysis. 2nd ed
• Coding of a source with unknown but ordered probabilities
• Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems
• Papers on probability, statistics and statistical physics. Ed. by R. D. Rosenkrantz.
• I-divergence geometry of probability distributions and minimization problems
• Jeffreys' prior is asymptotically least favorable under entropy risk
• Basic concepts, identities and inequalities -- the toolkit of information theory
• Maximum entropy fundamentals
• Coherent dispersion criteria for optimal experimental design
• An algorithm for calculating \(\Gamma\)-minimax decision rules under generalized moment conditions.
• Shannon optimal priors on independent identically distributed statistical experiments converge weakly to Jeffrey's prior
• On a Measure of the Information Provided by an Experiment
• Information Theory and Statistical Mechanics
• General entropy criteria for inverse problems, with applications to data compression, pattern classification, and cluster analysis
• Information-theoretic asymptotics of Bayes methods
• A source matching approach to finding minimax codes
• Random coding strategies for minimum entropy
• A general minimax result for relative entropy
• Asymptotic minimax regret for data compression, gambling, and prediction
• Maximum entropy versus minimum risk and applications to some classical discrete distributions
• A strong version of the redundancy-capacity theorem of universal coding
• Maximum Entropy Reconstruction Using Derivative Information, Part 1: Fisher Information and Convex Duality
• Uncertainty, Information, and Sequential Experiments
• Convex Analysis
• Γ-Minimax: A Paradigm for Conservative Robust Bayesians
• Relative loss bounds for on-line density estimation with the exponential family of distributions

This page was built for publication: Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory