Minimum complexity density estimation

DOI10.1109/18.86996zbMath0743.62003OpenAlexW2095734615MaRDI QIDQ3981153

Thomas M. Cover, Andrew R. Barron

Publication date: 26 June 1992

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

Full work available at URL: https://semanticscholar.org/paper/89abe70d94307ec06369febd092a418ce1afd7ce

zbMATH Keywords

rate of convergenceconvergence ratesmodel selectionKolmogorov complexityminimum description-length principleuniversal data compressionindex of resolvabilitybounds on redundancydiscovery of probability lawsinfinitely complex densitiesminimum complexity density estimatorsresolvability of functions

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Information theory (general) (94A15) Statistical aspects of information-theoretic topics (62B10)

Related Items (67)

Information optimality and Bayesian modelling ⋮ Multiscale likelihood analysis and complexity penalized estimation. ⋮ Model Selection via the VC-Dimension ⋮ Counting probability distributions: Differential geometry and model selection ⋮ Adaptive log-density estimation ⋮ Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth ⋮ Minimal penalties for Gaussian model selection ⋮ High-dimensional penalty selection via minimum description length principle ⋮ Tractability of batch to sequential conversion ⋮ Model selection by bootstrap penalization for classification ⋮ Suboptimal behavior of Bayes and MDL in classification under misspecification ⋮ Statistical estimation with model selection ⋮ PREDICTION/ESTIMATION WITH SIMPLE LINEAR MODELS: IS IT REALLY THAT SIMPLE? ⋮ On-line maximum likelihood prediction with respect to general loss functions ⋮ Unnamed Item ⋮ Statistical Problem Classes and Their Links to Information Theory ⋮ From \(\varepsilon\)-entropy to KL-entropy: analysis of minimum information complexity density estima\-tion ⋮ Schwarz, Wallace, and Rissanen: Intertwining Themes in Theories of Model Selection ⋮ Estimation Strategies for Censored Lifetimes with a Lexis‐Diagram Type Model ⋮ Locally uniform prior distributions ⋮ Rates of convergence of estimates, Kolmogorov's entropy and the dimensionality reduction principle in regression ⋮ Estimator selection: a new method with applications to kernel density estimation ⋮ USING THE MUTUAL INFORMATION COEFFICIENT TO IDENTIFY LAGS IN NONLINEAR MODELS ⋮ A Bernstein-type inequality for suprema of random processes with applications to model selection in non-Gaussian regression ⋮ Joint production in stochastic non-parametric envelopment of data with firm-specific directions ⋮ Data driven versions of pearson's chisquare test for uniformity ⋮ Estimator selection with respect to Hellinger-type risks ⋮ A general framework for Bayes structured linear models ⋮ Parametric or nonparametric? A parametricness index for model selection ⋮ The decomposed normalized maximum likelihood code-length criterion for selecting hierarchical latent variable models ⋮ Catching up Faster by Switching Sooner: A Predictive Approach to Adaptive Estimation with an Application to the AIC–BIC Dilemma ⋮ Model selection based on minimum description length ⋮ Density estimation through convex combinations of densities: Approximation and estimation bounds ⋮ Consistency of discrete Bayesian learning ⋮ Identification of probabilities ⋮ The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder). ⋮ Data compression and histograms ⋮ Links between probabilistic automata and hidden Markov models: probability distributions, learning models and induction algorithms ⋮ A Computationally Efficient Method for Nonparametric Modeling of Neural Spiking Activity with Point Processes ⋮ A new algorithm for fixed design regression and denoising ⋮ Adaptive nonparametric confidence sets ⋮ Predictability, Complexity, and Learning ⋮ Model selection for Poisson processes with covariates ⋮ Unnamed Item ⋮ Mixing least-squares estimators when the variance is unknown ⋮ Theory of Classification: a Survey of Some Recent Advances ⋮ Oracle posterior contraction rates under hierarchical priors ⋮ Estimating the intensity of a random measure by histogram type estimators ⋮ Bayesian goodness-of-fit testing using infinite-dimensional exponential families ⋮ Information theory and superefficiency ⋮ Prequential analysis of complex data with adaptive model reselection ⋮ Subset Selection in Linear Regression using Sequentially Normalized Least Squares: Asymptotic Theory ⋮ Adaptive Estimation of Hazard Rate with Censored Data ⋮ Gaussian model selection with an unknown variance ⋮ Covariate selection for accelerated failure time data ⋮ Post-Model-Selection Method for Density Estimation ⋮ Unnamed Item ⋮ Wedgelets: Nearly minimax estimation of edges ⋮ Information-theoretic determination of minimax rates of convergence ⋮ Minimum description length revisited ⋮ Combining different procedures for adaptive regression ⋮ Statistical Inference, Occam's Razor, and Statistical Mechanics on the Space of Probability Distributions ⋮ Adaptive estimation in autoregression or \(\beta\)-mixing regression via model selection ⋮ Consistent estimation of mixture complexity. ⋮ Sequential predictions based on algorithmic complexity ⋮ Convergence rates for the minimum complexity estimator of counting process intensities^∗ ⋮ Model selection for regression on a random design

This page was built for publication: Minimum complexity density estimation