The stochastic auxiliary problem principle in Banach spaces: measurability and convergence
From MaRDI portal
Publication:5097016
Abstract: The stochastic Auxiliary Problem Principle (APP) algorithm is a general Stochastic Approximation (SA) scheme that turns the resolution of an original optimization problem into the iterative resolution of a sequence of auxiliary problems. This framework has been introduced to design decomposition-coordination schemes but also encompasses many well-known SA algorithms such as stochastic gradient descent or stochastic mirror descent. We study the stochastic APP in the case where the iterates lie in a Banach space and we consider an additive error on the computation of the subgradient of the objective. In order to derive convergence results or efficiency estimates for a SA scheme, the iterates must be random variables. This is why we prove the measurability of the iterates of the stochastic APP algorithm. Then, we extend convergence results from the Hilbert space case to the Banach space case. Finally, we derive efficiency estimates for the function values taken at the averaged sequence of iterates or at the last iterate, the latter being obtained by adapting the concept of modified Fej{'e}r monotonicity to our framework.
Recommendations
- Stochastic approximation algorithm for minimax problems
- Iterative methods of solving stochastic convex feasibility problems and applications
- Approximating stationary points of stochastic optimization problems in Banach space
- Ergodic convergence of a stochastic proximal point algorithm
- Robust Stochastic Approximation Approach to Stochastic Programming
Cites work
- scientific article; zbMATH DE number 3939101 (Why is no real title available?)
- scientific article; zbMATH DE number 3738591 (Why is no real title available?)
- scientific article; zbMATH DE number 3790208 (Why is no real title available?)
- scientific article; zbMATH DE number 1043533 (Why is no real title available?)
- scientific article; zbMATH DE number 1376935 (Why is no real title available?)
- scientific article; zbMATH DE number 3449561 (Why is no real title available?)
- scientific article; zbMATH DE number 765034 (Why is no real title available?)
- scientific article; zbMATH DE number 823377 (Why is no real title available?)
- scientific article; zbMATH DE number 3244500 (Why is no real title available?)
- A Stochastic Approximation Method
- A stopping rule for stochastic approximation
- A stopping rule for the Robbins-Monro method
- Acceleration of Stochastic Approximation by Averaging
- Convergence of stochastic proximal gradient algorithm
- Convex analysis and measurable multifunctions
- Convex analysis and monotone operator theory in Hilbert spaces
- Convex optimization: algorithms and complexity
- Decomposition/Coordination Algorithms in Stochastic Optimization
- Epi-convergence of sequences of normal integrands and strong consistency of the maximum likelihood estimator
- Introductory lectures on convex optimization. A basic course.
- Modified Fejér sequences and applications
- On perturbed proximal gradient algorithms
- Optimization by decomposition and coordination: A unified approach
- Projected stochastic gradients for convex constrained problems in Hilbert spaces
- Robust Stochastic Approximation Approach to Stochastic Programming
- Stochastic Estimation of the Maximum of a Regression Function
- Stochastic optimal control. The discrete time case
- Stochastic proximal gradient methods for nonconvex problems in Hilbert spaces
This page was built for publication: The stochastic auxiliary problem principle in Banach spaces: measurability and convergence
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5097016)
