Unifying mirror descent and dual averaging
From MaRDI portal
(Redirected from Unifying mirror descent and dual averaging)
Abstract: We introduce and analyze a new family of first-order optimization algorithms which generalizes and unifies both mirror descent and dual averaging. Within the framework of this family, we define new algorithms for constrained optimization that combines the advantages of mirror descent and dual averaging. Our preliminary simulation study shows that these new algorithms significantly outperform available methods in some situations.
Recommendations
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- Linear coupling: an ultimate unification of gradient and mirror descent
- Duality between subgradient and conditional gradient methods
- Primal-dual mirror descent method for constraint stochastic optimization problems
- A generalized online mirror descent with applications to classification and regression
Cites work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A survey of algorithms and analysis for adaptive online learning
- Algorithms of inertial mirror descent in convex problems of stochastic optimization
- An optimal method for stochastic composite optimization
- Asymptotic optimality in stochastic optimization
- Convergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions
- Convex Analysis
- Convex optimization: algorithms and complexity
- Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
- Dual extrapolation and its applications to solving variational inequalities and related problems
- Dual subgradient algorithms for large-scale nonsmooth learning problems
- scientific article; zbMATH DE number 3790208 (Why is no real title available?)
- scientific article; zbMATH DE number 3296905 (Why is no real title available?)
- Learning by mirror averaging
- Manifold identification in dual averaging for regularized stochastic online learning
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- Online learning and online convex optimization
- Optimal distributed online prediction using mini-batches
- Prediction, Learning, and Games
- Primal-dual subgradient methods for convex problems
- Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
- Quasi-monotone subgradient methods for nonsmooth convex minimization
- Recursive aggregation of estimators by the mirror descent algorithm with averaging
- Regret analysis of stochastic and nonstochastic multi-armed bandit problems
- Regret bounds and minimax policies under partial monitoring
- Regret in online combinatorial optimization
- Robust Stochastic Approximation Approach to Stochastic Programming
- Smooth minimization of non-smooth functions
Cited in
(10)- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- Hedge algorithm and dual averaging schemes
- Recursive aggregation of estimators by the mirror descent algorithm with averaging
- Linear coupling: an ultimate unification of gradient and mirror descent
- Stochastic approximation versus sample average approximation for Wasserstein barycenters
- Stochastic incremental mirror descent algorithms with Nesterov smoothing
- Learning Stationary Nash Equilibrium Policies in n-Player Stochastic Games with Independent Chains
- MirrorCBO: a consensus-based optimization method in the spirit of mirror descent
- Dual averaging algorithm with memory mechanism for nonsmooth optimization problems
- Learning by mirror averaging
This page was built for publication: Unifying mirror descent and dual averaging
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6038659)
