Minimum complexity regression estimation with weakly dependent observations
From MaRDI portal
Publication:4336394
DOI10.1109/18.556602zbMath0868.62015MaRDI QIDQ4336394
Elias Masry, Dharmendra S. Modha
Publication date: 5 August 1997
Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/5bd08682ef3da61779256ac4015ef3c86a1e94c7
neural networks; Bernstein inequality; rates of convergence; parametric models; dependent observations; strongly mixing processes; Fourier-transform-type representation; indices of resolvability; minimum complexity regression estimation; strongly mixing observations
62M10: Time series, auto-correlation, regression, etc. in statistics (GARCH)
41A17: Inequalities in approximation (Bernstein, Jackson, Nikol'ski?-type inequalities)
62B10: Statistical aspects of information-theoretic topics
Related Items
Unnamed Item, Model selection for (auto-)regression with dependent data, RISK MINIMIZATION FOR TIME SERIES BINARY CHOICE WITH VARIABLE SELECTION, Non parametric learning approach to estimate conditional quantiles in the dependent functional data case, Online regularized pairwise learning with non-i.i.d. observations, Adaptive wavelet estimation of a function from an m-dependent process with possibly unbounded m, Optimal rate for support vector machine regression with Markov chain samples, Wavelet Estimation of a Density in a GARCH-type Model, Learning Theory Estimates with Observations from General Stationary Stochastic Processes, Finite sample properties of system identification of ARX models under mixing conditions, Regularized least square regression with unbounded and dependent sampling, An oracle inequality for regularized risk minimizers with strongly mixing observations, Generalization bounds of ERM algorithm with Markov chain samples, Learning from regularized regression algorithms with \(p\)-order Markov chain sampling, Generalization bounds of ERM algorithm with \(V\)-geometrically ergodic Markov chains, On the adaptive wavelet deconvolution of a density for strong mixing sequences, Adaptive estimation of an additive regression function from weakly dependent data, Adaptive wavelet estimation of a biased density for strongly mixing sequences, Learning performance of Tikhonov regularization algorithm with geometrically beta-mixing observations, Classification with non-i.i.d. sampling, Generalization performance of least-square regularized regression algorithm with Markov chain samples, Convergence rate for the moving least-squares learning with dependent sampling, Regularized least square regression with dependent samples, An exponential inequality under weak dependence, Complexity-penalized estimation of minimum volume sets for dependent data, A note on application of integral operator in learning theory, Learning from uniformly ergodic Markov chains, Estimation and approximation bounds for gradient-based reinforcement learning, Orthogonal series estimates on strong spatial mixing data, An exponential inequality for U-statistics under mixing conditions, Exploiting random walks for learning, The generalization performance of ERM algorithm with strongly mixing observations, Minimum Hellinger distance estimation for discretely observed stochastic processes using recursive kernel density estimator, Exponential inequalities for nonstationary Markov chains, Recovery guarantees for polynomial coefficients from weakly dependent data with outliers, Learning performance of regularized regression with multiscale kernels based on Markov observations, Least-square regularized regression with non-iid sampling, Generalization performance of Gaussian kernels SVMC based on Markov sampling, Learning rates of regularized regression for exponentially strongly mixing sequence, Fast learning from \(\alpha\)-mixing observations, The performance bounds of learning machines based on exponentially strongly mixing sequences, Learning from non-irreducible Markov chains, Measuring the Capacity of Sets of Functions in the Analysis of ERM, INDEFINITE KERNEL NETWORK WITH DEPENDENT SAMPLING, Least-squares regularized regression with dependent samples andq-penalty, ℓ1-Norm support vector machine for ranking with exponentially strongly mixing sequence, PAC learning in non-linear FIR models, Learning from Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers, Regression learning with non-identically and non-independently sampling, Estimation of a Cumulative Distribution Function Under Interval Censoring “case 1” Via Warped Wavelets, A Note on Nonparametric Regression with β-Mixing Sequences
