On fixed gain recursive estimators with discontinuity in the parameters

DOI10.1051/PS/2018019zbMath1420.62359arXiv1609.05166OpenAlexW2963672576MaRDI QIDQ4967798

Sotirios Sabanis, Huy N. Chau, Chaman Kumar, Miklós Rásonyi

Publication date: 11 July 2019

Published in: ESAIM: Probability and Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1609.05166

zbMATH Keywords

adaptive controlrecursive estimatorsstochastic gradientnon-Markovian dynamicsmixing processesfixed gainparameter discontinuity

Mathematics Subject Classification ID

Stochastic approximation (62L20) Stochastic stability in control theory (93E15) Stochastic learning and adaptive control (93E35)

Related Items (6)

Stochastic gradient Hamiltonian Monte Carlo for non-convex learning ⋮ Optimising portfolio diversification and dimensionality ⋮ Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization ⋮ Convergence of the Kiefer–Wolfowitz algorithm in the presence of discontinuities ⋮ On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case ⋮ On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Analysis of a simple self-organizing process
• Strong approximation of the recursive prediction error estimator of the parameters of an ARMA process
• On Rissanen's predictive stochastic complexity for stationary ARMA processes
• On dichotomies for solutions of \(n\)-th order linear differential equations
• Long memory in continuous-time stochastic volatility models
• Convergence of Markovian Stochastic Approximation with Discontinuous Dynamics
• Stochastic approximation with averaging innovation applied to Finance
• Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
• A Representation Theorem for the Error of Recursive Estimators
• On the statistical analysis of quantized Gaussian AR(1) processes
• On a class of mixing processes
• Rate of Convergence of Recursive Estimators
• AR( infinity ) estimation and nonparametric stochastic complexity
• Regression Quantiles
• Some Averaging and Stability Results for Random Differential Equations
• Convergence of the one-dimensional Kohonen algorithm
• Iterated Random Functions
• Weak convergence and local stability properties of fixed step size recursive algorithms
• Volatility is rough
• Convergence analysis of an adaptive filter equipped with the sign-sign algorithm
• Modeling uncertainty. An examination of stochastic theory, methods, and applications

This page was built for publication: On fixed gain recursive estimators with discontinuity in the parameters