General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
From MaRDI portal
Publication:1740634
DOI10.1007/s00211-019-01024-yzbMath1464.62366arXiv1506.05482OpenAlexW2914255806WikidataQ128443017 ScholiaQ128443017MaRDI QIDQ1740634
Thomas Müller-Gronbach, Steffen Dereich
Publication date: 2 May 2019
Published in: Numerische Mathematik (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1506.05482
Computational methods for problems pertaining to statistics (62-08) Monte Carlo methods (65C05) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Stochastic approximation (62L20)
Related Items (13)
A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions ⋮ Full error analysis for the training of deep neural networks ⋮ Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation ⋮ (Non)-penalized multilevel methods for non-uniformly log-concave distributions ⋮ Multi-index antithetic stochastic gradient algorithm ⋮ A randomized multi-index sequential Monte Carlo method ⋮ Multilevel Monte Carlo Approximation of Functions ⋮ Sparse approximation of multilinear problems with applications to kernel-based methods in UQ ⋮ General multilevel adaptations for stochastic approximation algorithms. II: CLTs ⋮ Solving the Kolmogorov PDE by means of deep learning ⋮ Evaluating visual properties via robust HodgeRank ⋮ Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization ⋮ Unbiased MLMC Stochastic Gradient-Based Optimization of Bayesian Experimental Designs
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Multi-level stochastic approximation algorithms
- Almost sure approximations to the Robbins-Monro and Kiefer-Wolfowitz processes with dependent noise
- New method of stochastic approximation type
- Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing
- On the almost sure asymptotic behaviour of stochastic algorithm
- Some results about averaging in stochastic approximation
- Stochastic algorithms
- Stochastic Approximation with Averaging of the Iterates: Optimal Asymptotic Rate of Convergence for General Processes
- The Malliavin Calculus and Related Topics
- Multilevel Monte Carlo Path Simulation
- On the Law of the Iterated Logarithm in Stochastic Approximation Processes
- Limit theorems for weighted sums and stochastic approximation processes
- A Stochastic Approximation Method
- Stochastic approximation
This page was built for publication: General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type