Fisher information and stochastic complexity
From MaRDI portal
Publication:4879988
DOI10.1109/18.481776zbMath0856.94006OpenAlexW2068782468MaRDI QIDQ4879988
Publication date: 20 February 1997
Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/18.481776
Fisher informationcentral limit theoremmaximum-likelihood estimatesparametric processesstochastic complexitycode lengthmaximum-likelihood code
Related Items
Law of iterated logarithm and consistent model selection criterion in logistic regression, Information optimality and Bayesian modelling, Counting probability distributions: Differential geometry and model selection, Application of the evidence procedure to the estimation of wireless channels, Bayes factors, relations to minimum description length, and overlapping model classes, High-dimensional penalty selection via minimum description length principle, Thou shalt identify! The identifiability of two high-threshold models in confidence-rating recognition (and super-recognition) paradigms, A linear-time algorithm for computing the multinomial stochastic complexity, Quantum Fisher information dynamics in the presence of intrinsic decoherence, Application of the Fisher-Rao metric to structure detection, Bayesian model learning based on predictive entropy, A methodology for developing Bayesian networks: an application to information technology (IT) implementation, A Note on the Applied Use of MDL Approximations, Using the Bayesian Shtarkov solution for predictions, Metabolic cost of neuronal information in an empirical stimulus-response model, Stochastic complexity in learning, A network of autoregressive processing units for time series modeling, Statistical Problem Classes and Their Links to Information Theory, An Introduction to Coding Theory and the Two-Part Minimum Description Length Principle, Schwarz, Wallace, and Rissanen: Intertwining Themes in Theories of Model Selection, Probabilistic Models for Bacterial Taxonomy, Tracking Multiple Targets Using Binary Decisions From Wireless Sensor Networks, On model selection, Bayesian networks, and the Fisher information integral, Test for homogeneity of several populations by stochastic complexity, A tutorial on Fisher information, Constructive reinforcement learning, The effect of interspike interval statistics on the information gain under the rate coding hypothesis, Testing order constraints: qualitative differences between Bayes factors and normalized maximum likelihood, Predicting a binary sequence almost as well as the optimal biased coin, Scalability of the Bayesian optimization algorithm., The flexibility of models of recognition memory: the case of confidence ratings, Optimal weights decoding of \(M\)-ary suprathreshold stochastic resonance in stochastic pooling network, Selecting amongst multinomial models: an apologia for normalized maximum likelihood, Model-based multidimensional clustering of categorical data, Regarding the complexity of additive clustering models: comment on Lee (2001)., The generalized universal law of generalization., Prediction in several conventional contexts, MDL Mean Function Selection in Semiparametric Kernel Regression Models, Information gains expected from separate and joint measurements of N identical spin-1/2 systems: Noninformative Bayesian analyses, Chentsov's theorem for exponential families, Ensuring privacy with constrained additive noise by minimizing Fisher information, Optimal Sampling of Parametric Families: Implications for Machine Learning, Mutual Information, Fisher Information, and Efficient Coding, The decomposed normalized maximum likelihood code-length criterion for selecting hierarchical latent variable models, Latent Features in Similarity Judgments: A Nonparametric Bayesian Approach, Learning genetic population structures using minimization of stochastic complexity, The flexibility of models of recognition memory: an analysis by the minimum-description length principle, Hierarchical two-part MDL code for multinomial distributions, Assessing model mimicry using the parametric bootstrap., Stochastic variable selection strategies for zero-inflated models, Model selection based on minimum description length, Sparse model selection in the highly under-sampled regime, Machine learning based congestive heart failure detection using feature importance ranking of multimodal features, An Information-Geometric Approach to Learning Bayesian Network Topologies from Data, Consistency of discrete Bayesian learning, Information-Theoretic Bounds and Approximations in Neural Population Coding, GARCH model selection criteria, Unnamed Item, Subspace Information Criterion for Model Selection, Quantifying Neurotransmission Reliability Through Metrics-Based Information Analysis, Clustgrams: an extension to histogram densities based on the minimum description length principle, Jeffreys versus Shtarkov distributions associated with some natural exponential families, Population sizing for inductive linkage identification, Discrepancy risk model selection test theory for comparing possibly misspecified or nonnested models, Explanatory and creative alternatives to the MDL principle, Variable selection in linear regression: several approaches based on normalized maximum likelihood, A lower bound on compression of unknown alphabets, Model selection by sequentially normalized least squares, On the minimum description length complexity of multinomial processing tree models, A Bayesian analysis of retention functions, On discriminative Bayesian network classifiers and logistic regression, Predictability, Complexity, and Learning, Complexity through nonextensivity, Bayesian nonparametric model selection and model testing, Accumulative prediction error and the selection of time series models, Model selection by normalized maximum likelihood, An empirical study of minimum description length model selection with infinite parametric complexity, Model selection for the rate problem: a comparison of significance testing, Bayesian and minimum description length statistical inference, Nonparametric Regression as an Example of Model Choice, Model selection by minimum description length: lower-bound sample sizes for the Fisher information approximation, Bayesian unsupervised classification framework based on stochastic partitions of data and a parallel search strategy, Minimum message length inference of the Poisson and geometric models using heavy-tailed prior distributions, Uncertainty quantification for principal component regression, On the Complexity of Logistic Regression Models, Spatial sampling design based on stochastic complexity., Minimum message length shrinkage estimation, On some properties of the NML estimator for Bernoulli strings, On the computation of entropy prior complexity and marginal prior distribution for the Bernoulli model, A predictive approach to measuring the strength of statistical evidence for single and multiple comparisons, Minimum description length revisited, A comparison of automatic histogram constructions, Failure-time prediction, Stochastic complexity and model selection from incomplete data, On model selection via stochastic complexity in robust linear regression, Parameter Estimation in Multiple Dynamic Synaptic Coupling Model Using Bayesian Point Process State-Space Modeling Framework, Application of minimum description length criterion to assess the complexity of models in mathematical immunology, Optimal work extraction and the minimum description length principle, Bayesian predictiveness, exchangeability and sufficientness in bacterial taxonomy
