Mirror descent and nonlinear projected subgradient methods for convex optimization.

DOI10.1016/S0167-6377(02)00231-6MaRDI QIDQ1811622zbMATH OpenFDO

Authors Amir Beck, Marc Teboulle

Publication date 17 June 2003

Published in Operations Research Letters (Search for Journal in Brave)

zbMATH Keywords

projectionsconvergenceNonlinearComplexity analysisGlobal rate ofMirror descent algorithmsNonsmooth convex minimizationProjected subgradient methodsRelative entropy

Mathematics Subject Classification ID

Convex programming (90C25) Methods of reduced gradient type (90C52)

Recommendations

• Mirror descent and convex optimization problems with non-smooth inequality constraints
• Mirror descent and constrained online optimization problems
• Algorithms of inertial mirror descent in stochastic convex optimization problems
• Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex
• Unifying mirror descent and dual averaging

Cites work

• scientific article; zbMATH DE number 1818892 (Why is no real title available?)
• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• scientific article; zbMATH DE number 3296905 (Why is no real title available?)
• scientific article; zbMATH DE number 3365044 (Why is no real title available?)
• An Interior Proximal Algorithm and the Exponential Multiplier Method for Semidefinite Programming
• An iterative row-action method for interval convex programming
• Convergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions
• Entropic Proximal Mappings with Applications to Nonlinear Programming
• Incremental subgradient methods for nondifferentiable optimization
• Monotone Operators and the Proximal Point Algorithm
• On the Optimum Rate of Transmitting Information
• Proximal Minimization Methods with Generalized Bregman Functions
• The ordered subsets mirror descent optimization method with applications to tomography
• Variational Analysis

Cited in

(only showing first 100 items - show all)

• Accelerated training of max-margin Markov networks with kernels
• A survey of algorithms and analysis for adaptive online learning
• Scale-free online learning
• Unifying mirror descent and dual averaging
• Bregman proximal gradient algorithms for deep matrix factorization
• On the convergence time of a natural dynamics for linear programming
• A family of subgradient-based methods for convex optimization problems in a unifying framework
• Mirror variational transport: a particle-based algorithm for distributional optimization on constrained domains
• Essentials of numerical nonsmooth optimization
• Distributed inertial online game algorithm for tracking generalized Nash equilibria
• Differential equation-constrained optimization with stochasticity
• On the convergence time of a natural dynamics for linear programming
• A telescopic Bregmanian proximal gradient method without the global Lipschitz continuity assumption
• Optimal subgradient methods: computational properties for large-scale linear inverse problems
• Solving variational inequalities with monotone operators on domains given by linear minimization oracles
• Mirror descent and convex optimization problems with non-smooth inequality constraints
• Revisiting Deep Structured Models for Pixel-Level Labeling with Gradient-Based Inference
• Conformal mirror descent with logarithmic divergences
• Quasi-subgradient methods with Bregman distance for quasi-convex feasibility problems
• Approximation accuracy, gradient methods, and error bound for structured convex optimization
• A derivative-free comirror algorithm for convex optimization
• Distributed Bayesian learning with stochastic natural gradient expectation propagation and the posterior server
• Faster randomized block sparse Kaczmarz by averaging
• Network manipulation algorithm based on inexact alternating minimization
• Modified accelerated Bregman projection methods for solving quasi-monotone variational inequalities
• On risk concentration for convex combinations of linear estimators
• Inertial alternating generalized forward-backward splitting for image colorization
• Analysis of singular value thresholding algorithm for matrix completion
• Convergence of online mirror descent
• Stochastic incremental mirror descent algorithms with Nesterov smoothing
• Multi-manifold matrix decomposition for data co-clustering
• An incremental mirror descent subgradient algorithm with random sweeping and proximal step
• Projected subgradient minimization versus superiorization
• The optimal dynamic regret for smoothed online convex optimization with squared \(l_2\) norm switching costs
• An entropic Landweber method for linear ill-posed problems
• Generalized conditional gradient for sparse estimation
• The rate of convergence of Bregman proximal methods: local geometry versus regularity versus sharpness
• Distributed adaptive online learning for convex optimization with weight decay
• Near-optimal discrete optimization for experimental design: a regret minimization approach
• Subgradient methods for saddle-point problems
• Learning Stationary Nash Equilibrium Policies in \(n\)-Player Stochastic Games with Independent Chains
• Fast iterative regularization by reusing data
• Smooth over-parameterized solvers for non-smooth structured optimization
• First-order methods for convex optimization
• A penalty algorithm for solving convex separable knapsack problems
• Analysis of Online Composite Mirror Descent Algorithm
• Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and Prediction
• A gradient descent perspective on Sinkhorn
• The cyclic block conditional gradient method for convex optimization problems
• Optimization-based calibration of simulation input models
• Learning in games with continuous action sets and unknown payoff functions
• Essentials of numerical nonsmooth optimization
• Fastest rates for stochastic mirror descent methods
• Interior-point-based online stochastic bin packing
• Problems of differential and topological diagnostics. IV: The case of exact trajectorial measurements
• Stochastic mirror descent method for linear ill-posed problems in Banach spaces
• Problems of differential and topological diagnostics. V: The case of trajectorial measurements with error
• Implicit regularization with strongly convex bias: Stability and acceleration
• Data-Driven Mirror Descent with Input-Convex Neural Networks
• Point process estimation with Mirror Prox algorithms
• Generalized stochastic Frank-Wolfe algorithm with stochastic ``substitute gradient for structured convex optimization
• Parsimonious system identification from fragmented quantised measurements
• Stochastic mirror descent for convex optimization with consensus constraints
• Interior projection-like methods for monotone variational inequalities
• Subgradient and bundle methods for nonsmooth optimization
• Inverse reinforcement learning in contextual MDPs
• Interior quasi-subgradient method with non-Euclidean distances for constrained quasi-convex optimization problems in Hilbert spaces
• An accelerated stochastic mirror descent method
• Statistical computational learning
• Bregman methods for large-scale optimization with applications in imaging
• Homotopic policy mirror descent: policy convergence, algorithmic regularization, and improved sample complexity
• Distributed mirror descent algorithm over unbalanced digraphs based on gradient weighting technique
• Mirror descent and constrained online optimization problems
• Natural gradient for combined loss using wavelets
• Accelerated stochastic algorithms for convex-concave saddle-point problems
• Stochastic block mirror descent methods for nonsmooth and stochastic optimization
• Scalable estimation strategies based on stochastic approximations: classical results and new insights
• On linear convergence of non-Euclidean gradient methods without strong convexity and Lipschitz gradient continuity
• Optimal Scheduling of Entropy Regularizer for Continuous-Time Linear-Quadratic Reinforcement Learning
• Problems of differential and topological diagnostics. VI: Statistical solving of the problem of differential diagnostics
• Entropic Trust Region for Densest Crystallographic Symmetry Group Packings
• A dual method for minimizing a nonsmooth objective over one smooth inequality constraint
• On the ergodic convergence rates of a first-order primal-dual algorithm
• New results on subgradient methods for strongly convex optimization problems with a unified analysis
• Algorithms of inertial mirror descent in convex problems of stochastic optimization
• Bregman-Golden ratio algorithms for variational inequalities
• The CoMirror algorithm for solving nonsmooth constrained convex problems
• Problems of differential and topological diagnostics. II: Problem of differential diagnostics
• Problems of differential and topological diagnostics. III: The checking problem
• Level-set methods for convex optimization
• Mirror descent algorithms for minimizing interacting free energy
• Optimal complexity and certification of Bregman first-order methods
• Problems of differential and topological diagnostics. I: Motion equations and classification of malfunctions
• A simplified view of first order methods for optimization
• Re-examination of Bregman functions and new properties of their divergences
• Dual space preconditioning for gradient descent
• On modification of an adaptive stochastic mirror descent algorithm for convex optimization problems with functional constraints
• Accelerated first-order methods for large-scale convex optimization: nearly optimal complexity under strong convexity
• Stochastic gradient Markov chain Monte Carlo
• A non-linear conjugate gradient in dual space for \(L_p\)-norm regularized non-linear least squares with application in data assimilation

This page was built for publication: Mirror descent and nonlinear projected subgradient methods for convex optimization.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1811622)