Convergence of online mirror descent

DOI10.1016/j.acha.2018.05.005zbMath1494.68219arXiv1802.06357OpenAlexW2803423166WikidataQ129764098 ScholiaQ129764098MaRDI QIDQ2278461

Ding-Xuan Zhou, Yunwen Lei

Publication date: 5 December 2019

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1802.06357

zbMATH Keywords

convergence analysislearning theoryonline learningBregman distancemirror descent

Mathematics Subject Classification ID

Convex programming (90C25) Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) Stochastic approximation (62L20) Online algorithms; streaming algorithms (68W27)

Related Items

Block coordinate type methods for optimization and learning ⋮ Federated learning for minimizing nonsmooth convex loss functions ⋮ Distributed learning and distribution regression of coefficient regularization ⋮ Analogues of Switching Subgradient Schemes for Relatively Lipschitz-Continuous Convex Programming Problems ⋮ Analysis of singular value thresholding algorithm for matrix completion ⋮ Error analysis of the kernel regularized regression based on refined convex losses and RKBSs

Uses Software

• AIR tools

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unregularized online learning algorithms with general loss functions
• Multi-kernel regularized classifiers
• A randomized Kaczmarz algorithm with exponential convergence
• Online gradient descent learning algorithms
• Sharp uniform convexity and smoothness inequalities for trace norms
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Almost sure convergence of the Kaczmarz algorithm with random measurements
• Online regularized learning with pairwise loss functions
• AIR tools -- a MATLAB package of algebraic iterative reconstruction methods
• Online learning algorithms
• Incremental Subgradient Methods for Nondifferentiable Optimization
• Linearized Bregman iterations for compressed sensing
• Online Regularized Classification Algorithms
• Robust Stochastic Approximation Approach to Stochastic Programming
• Optimization Methods for Large-Scale Machine Learning
• Regularization schemes for minimum error entropy principle
• Thresholded spectral algorithms for sparse approximations
• Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization
• On Complexity Issues of Online Learning Algorithms
• Learning theory of distributed spectral algorithms
• Analysis of Online Composite Mirror Descent Algorithm
• Robust Estimation of a Location Parameter
• A Stochastic Approximation Method