An accelerated stochastic mirror descent method

DOI10.1007/S40305-023-00492-2MaRDI QIDQ6601963zbMATH OpenFDO

Authors Bo-Ou Jiang, Yaxiang Yuan

Publication date 11 September 2024

Published in Journal of the Operations Research Society of China (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S40305-023-00492-2

zbMATH Keywords

accelerationimportance samplingindependent samplinglarge-scale optimizationmirror descentvariance reduction

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Stochastic programming (90C15) Convex programming (90C25) Nonlinear programming (90C30)

Recommendations

• Fastest rates for stochastic mirror descent methods
• Primal-dual mirror descent method for constraint stochastic optimization problems
• Stochastic block mirror descent methods for nonsmooth and stochastic optimization
• Accelerated randomized mirror descent algorithms for composite non-strongly convex optimization
• Accelerated and unaccelerated stochastic gradient descent in model generality

Cites work

• A differential equation for modeling Nesterov's accelerated gradient method: theory and insights
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• A Stochastic Approximation Method
• Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• Analysis and design of optimization algorithms via integral quadratic constraints
• Incremental majorization-minimization optimization with application to large-scale machine learning
• Katyusha: the first direct acceleration of stochastic gradient methods
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
• Minimizing finite sums with the stochastic average gradient
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• On the local convergence of a stochastic semismooth Newton method for nonsmooth nonconvex optimization
• Optimization methods for large-scale machine learning
• Signal Recovery by Proximal Forward-Backward Splitting
• Some methods of speeding up the convergence of iteration methods
• Stochastic proximal quasi-Newton methods for non-convex composite optimization
• Understanding the acceleration phenomenon via high-resolution differential equations
• Universal method for stochastic composite optimization problems

Cited in

(1)

• Data-Driven Mirror Descent with Input-Convex Neural Networks

This page was built for publication: An accelerated stochastic mirror descent method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6601963)