Minimum complexity regression estimation with weakly dependent observations

DOI10.1109/18.556602zbMath0868.62015OpenAlexW2147303334MaRDI 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

zbMATH Keywords

neural networksBernstein inequalityrates of convergenceparametric modelsdependent observationsstrongly mixing processesFourier-transform-type representationindices of resolvabilityminimum complexity regression estimationstrongly mixing observations

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Inequalities in approximation (Bernstein, Jackson, Nikol'ski?-type inequalities) (41A17) Statistical aspects of information-theoretic topics (62B10)

Related Items (52)

Convergence rate for the moving least-squares learning with dependent sampling ⋮ Model selection for (auto-)regression with dependent data ⋮ Least-squares regularized regression with dependent samples andq-penalty ⋮ Wavelet Estimation of a Density in a GARCH-type Model ⋮ Estimation of a Cumulative Distribution Function Under Interval Censoring “case 1” Via Warped Wavelets ⋮ Regularized least square regression with dependent samples ⋮ An exponential inequality under weak dependence ⋮ Online regularized pairwise learning with non-i.i.d. observations ⋮ Minimum Hellinger distance estimation for discretely observed stochastic processes using recursive kernel density estimator ⋮ Adaptive wavelet estimation of a function from an m-dependent process with possibly unbounded m ⋮ Regularized least square regression with unbounded and dependent sampling ⋮ An oracle inequality for regularized risk minimizers with strongly mixing observations ⋮ PAC learning in non-linear FIR models ⋮ Exponential inequalities for nonstationary Markov chains ⋮ Orthogonal series estimates on strong spatial mixing data ⋮ Learning from Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers ⋮ Spectral algorithms for learning with dependent observations ⋮ Generalization bounds of ERM algorithm with Markov chain samples ⋮ Learning performance of Tikhonov regularization algorithm with geometrically beta-mixing observations ⋮ Regression learning with non-identically and non-independently sampling ⋮ Approximate minimum Hellinger distance estimation for diffusion processes using Euler's scheme ⋮ Learning rates of regularized regression for exponentially strongly mixing sequence ⋮ Learning from regularized regression algorithms with \(p\)-order Markov chain sampling ⋮ Learning from non-irreducible Markov chains ⋮ Generalization bounds of ERM algorithm with \(V\)-geometrically ergodic Markov chains ⋮ Recovery guarantees for polynomial coefficients from weakly dependent data with outliers ⋮ Fast learning from \(\alpha\)-mixing observations ⋮ The generalization performance of ERM algorithm with strongly mixing observations ⋮ On the adaptive wavelet deconvolution of a density for strong mixing sequences ⋮ Learning Theory Estimates with Observations from General Stationary Stochastic Processes ⋮ Classification with non-i.i.d. sampling ⋮ Adaptive estimation of an additive regression function from weakly dependent data ⋮ Generalization performance of least-square regularized regression algorithm with Markov chain samples ⋮ The performance bounds of learning machines based on exponentially strongly mixing sequences ⋮ An exponential inequality for U-statistics under mixing conditions ⋮ Learning performance of regularized regression with multiscale kernels based on Markov observations ⋮ Finite sample properties of system identification of ARX models under mixing conditions ⋮ Adaptive wavelet estimation of a biased density for strongly mixing sequences ⋮ A Note on Nonparametric Regression with β-Mixing Sequences ⋮ RISK MINIMIZATION FOR TIME SERIES BINARY CHOICE WITH VARIABLE SELECTION ⋮ Least-square regularized regression with non-iid sampling ⋮ Unnamed Item ⋮ Complexity-penalized estimation of minimum volume sets for dependent data ⋮ Measuring the Capacity of Sets of Functions in the Analysis of ERM ⋮ A note on application of integral operator in learning theory ⋮ Non parametric learning approach to estimate conditional quantiles in the dependent functional data case ⋮ Learning from uniformly ergodic Markov chains ⋮ Optimal rate for support vector machine regression with Markov chain samples ⋮ INDEFINITE KERNEL NETWORK WITH DEPENDENT SAMPLING ⋮ Generalization performance of Gaussian kernels SVMC based on Markov sampling ⋮ Exploiting random walks for learning ⋮ Estimation and approximation bounds for gradient-based reinforcement learning

This page was built for publication: Minimum complexity regression estimation with weakly dependent observations