Berry-Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms
From MaRDI portal
Publication:2137030
DOI10.3150/21-BEJ1336MaRDI QIDQ2137030
Publication date: 16 May 2022
Published in: Bernoulli (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2102.04923
Stein's methodM-estimatorsBerry-Esseen boundmultivariate normal approximationaveraged stochastic gradient descent algorithmsrandomized concentration inequality
Related Items (1)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Cramér type moderate deviation theorems for self-normalized processes
- On the rate of convergence in the multivariate CLT
- Multivariate normal approximation with Stein's method of exchangeable pairs under a general linearity condition
- Stein's method for diffusion approximations
- Rates of convergence in the asymptotic normality for some local maximum estimators
- On the dependence of the Berry-Esseen bound on dimension
- Weak convergence and empirical processes. With applications to statistics
- A multivariate Berry-Esseen theorem with explicit constants
- Normal approximation for nonlinear statistics using a concentration inequality approach
- The Berry-Esseen bound for minimum contrast estimates
- Further results on asymptotic normality. I
- Normal Approximation by Stein’s Method
- Robust Stochastic Approximation Approach to Stochastic Programming
- Acceleration of Stochastic Approximation by Averaging
- Asymptotic Statistics
- A Berry–Esséen Bound for M‐estimators
- Multivariate normal approximations by Stein's method and size bias couplings
- The accuracy of the normal approximation for estimates of vector parameters
- A Lyapunov-type Bound in Rd
This page was built for publication: Berry-Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms
