Algorithms of inertial mirror descent in convex problems of stochastic optimization
From MaRDI portal
Abstract: The goal is to modify the known method of mirror descent (MD), proposed by A.S. Nemirovsky and D.B. Yudin in 1979. The paper shows the idea of a new, so-called inertial MD method with the example of a deterministic optimization problem in continuous time. In particular, in the Euclidean case, the heavy ball method by B.T. Polyak is realized. It is noted that the new method does not use additional averaging. A discrete algorithm of inertial MD is described. The theorem on the upper bound on the error in the objective function is proved.
Recommendations
- Algorithms of inertial mirror descent in stochastic convex optimization problems
- On modification of an adaptive stochastic mirror descent algorithm for convex optimization problems with functional constraints
- Algorithms of robust stochastic optimization based on mirror descent method
- Primal-dual mirror descent method for constraint stochastic optimization problems
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
Cites work
- A differential equation for modeling Nesterov's accelerated gradient method: theory and insights
- Convex Analysis
- scientific article; zbMATH DE number 4164577 (Why is no real title available?)
- scientific article; zbMATH DE number 3997615 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- Introductory lectures on convex optimization. A basic course.
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- One class of methods of unconditional minimization of a convex function, having a high rate of convergence
- Quasi-monotone subgradient methods for nonsmooth convex minimization
- Recursive aggregation of estimators by the mirror descent algorithm with averaging
- Some methods of speeding up the convergence of iteration methods
- The elements of statistical learning. Data mining, inference, and prediction
- The ordered subsets mirror descent optimization method with applications to tomography
- Variational Analysis
Cited in
(16)- Algorithms of inertial mirror descent in stochastic convex optimization problems
- On stochastic mirror descent with interacting particles: convergence properties and variance reduction
- Hessian informed mirror descent
- Algorithms of robust stochastic optimization based on mirror descent method
- Mirror descent and convex optimization problems with non-smooth inequality constraints
- Ergodic mirror descent
- On stochastic subgradient mirror-descent algorithm with weighted averaging
- Tridimensional autonomous motion robust control of submersible ship based on averaged sub-gradient integral sliding mode approach
- On modification of an adaptive stochastic mirror descent algorithm for convex optimization problems with functional constraints
- Distributed stochastic inertial-accelerated methods with delayed derivatives for nonconvex problems
- Unifying mirror descent and dual averaging
- Non-quadratic proxy functions in mirror descent method applied to designing of robust controllers for nonlinear dynamic systems with uncertainty
- \(\varepsilon\)-Nash equilibrium of non-cooperative Lagrangian dynamic games based on the average sub-gradient robust integral sliding mode control
- Validation analysis of mirror descent stochastic approximation method
- Elements of randomized forecasting and its application to daily electrical load prediction in a regional power system
- A mirror descent algorithm for minimization of mean Poisson flow driven losses
This page was built for publication: Algorithms of inertial mirror descent in convex problems of stochastic optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1641948)
