Some remarks on MCMC estimation of spectra of integral operators

DOI10.3150/14-BEJ635zbMath1350.60027arXiv1311.7566OpenAlexW1954519420MaRDI QIDQ888474

Witold Bednorz, Radosław Adamczak

Publication date: 30 October 2015

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1311.7566

zbMATH Keywords

random matriceslaw of large numbersintegral operatorsspectrakernel operatorsMarkov chain Monte Carlo algorithmsempirical approximations

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Random matrices (probabilistic aspects) (60B20) Monte Carlo methods (65C05) Strong limit theorems (60F15) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Numerical analysis or methods applied to Markov chains (65C40) Integral operators (45P05) Integral operators (47G10)

Related Items

Computing the asymptotic distribution of second-order \(U\)- and \(V\)-statistics ⋮ Trace class Markov chains for the normal-gamma Bayesian shrinkage model ⋮ Trace-class Monte Carlo Markov chains for Bayesian multivariate linear regression with non-Gaussian errors ⋮ From random matrices to long range dependence ⋮ Random discretization of the finite Fourier transform and related kernel random matrices ⋮ Consistent estimation of the spectrum of trace class data augmentation algorithms

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Mercer theorem for RKHS on noncompact sets
• On nonlinear Markov chain Monte Carlo
• Markov chains and stochastic stability
• Bounds on regeneration times and limit theorems for subgeometric Markov chains
• Geometry on probability spaces
• On singular values of matrices with independent rows
• General state space Markov chains and MCMC algorithms
• A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
• The Hoffman-Wielandt inequality in infinite dimensions
• The law of large numbers for \(U\)-statistics under absolute regularity
• Renewal theory and computable convergence rates for geometrically erdgodic Markov chains
• Practical drift conditions for subgeometric rates of convergence.
• Random matrix approximation of spectra of integral operators
• A renewal approach to Markovian \(U\)-statistics
• Consistency of spectral clustering
• General Irreducible Markov Chains and Non-Negative Operators
• On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
• A splitting technique for Harris recurrent Markov chains
• A New Approach to the Limit Theory of Recurrent Markov Chains
• Limit theorems for functionals of ergodic Markov chains with general state space
• Strong laws for 𝐿- and 𝑢-statistics
• Mercer’s Theorem, Feature Maps, and Smoothing
• The Kendall theorem and its application to the geometric ergodicity of Markov chains
• Learning Theory