Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings
From MaRDI portal
Publication:2325397
DOI10.3150/19-BEJ1115zbMath1431.60080arXiv1806.02107OpenAlexW2976436354MaRDI QIDQ2325397
François Portier, Patrice Bertail
Publication date: 25 September 2019
Published in: Bernoulli (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1806.02107
Related Items
High dimensional regression for regenerative time-series: an application to road traffic modeling ⋮ Exponential inequalities for nonstationary Markov chains ⋮ Safe adaptive importance sampling: a mixture approach
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
- U-processes: Rates of convergence
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- Bounds on regeneration times and limit theorems for subgeometric Markov chains
- Regenerative block-bootstrap for Markov chains
- Subgaussian concentration inequalities for geometrically ergodic Markov chains
- Uniform central limit theorems for kernel density estimators
- General state space Markov chains and MCMC algorithms
- Basic properties of strong mixing conditions. A survey and some open questions
- A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
- Uniform limit theorems for Harris recurrent Markov chains
- A law of the logarithm for kernel density estimators
- On the central limit theorem for stationary mixing random fields
- Probability density estimation using delta sequences
- Sharper bounds for Gaussian and empirical processes
- Geometric ergodicity of Metropolis algorithms
- On the weak convergence of the empirical conditional copula under a simplifying assumption
- Edgeworth expansions of suitably normalized sample mean statistics for atomic Markov chains
- Quantitative bounds on convergence of time-inhomogeneous Markov chains
- Rates of strong uniform consistency for multivariate kernel density estimators. (Vitesse de convergence uniforme presque sûre pour des estimateurs à noyaux de densités multivariées)
- Weak convergence and empirical processes. With applications to statistics
- Rates of convergence of the Hastings and Metropolis algorithms
- Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
- Nonparametric Bayesian posterior contraction rates for discretely observed scalar diffusions
- Nonasymptotic bounds on the estimation error of MCMC algorithms
- Concentration inequalities for Markov chains by Marton couplings and spectral methods
- Uniform in bandwidth consistency of kernel-type function estimators
- Local Rademacher complexities
- Non-parametric Estimation of the Residual Distribution
- On Martingale Extensions of Vapnik–Chervonenkis Theory with Applications to Online Learning
- Sharp Bounds for the Tails of Functionals of Markov Chains
- Regenerative stochastic processes
- General Irreducible Markov Chains and Non-Negative Operators
- Empirical Processes with Applications to Statistics
- Mathematical Foundations of Infinite-Dimensional Statistical Models
- Markov Chains and Stochastic Stability
- UNIFORM CONVERGENCE RATES FOR KERNEL ESTIMATION WITH DEPENDENT DATA
- Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
- The Berry-Esseen theorem for functionals of discrete Markov chains
- Properties of uniform consistency of the kernel estimators of density and regression functions under dependence assumptions
- A splitting technique for Harris recurrent Markov chains
- A New Approach to the Limit Theory of Recurrent Markov Chains
- Asymptotic Statistics
- Limit theorems for functionals of ergodic Markov chains with general state space
- 10.1162/153244303321897690
- Integral estimation based on Markovian design
- Exponential inequalities for unbounded functions of geometrically ergodic Markov chains: applications to quantitative error bounds for regenerative Metropolis algorithms
- Empirical processes indexed by estimated functions
- Advanced Lectures on Machine Learning
- Contributions to Doeblin's theory of Markov processes
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Limit Theorems for Harris Markov Chains, II
- A regeneration proof of the central limit theorem for uniformly ergodic Markov chains
- An empirical process approach to the uniform consistency of kernel-type function estimators
- An adaptive Metropolis algorithm
- On consistency of kernel density estimators for randomly censored data: Rates holding uniformly over adaptive intervals
- On the asymptotics of \(Z\)-estimators indexed by the objective functions
