Manifold identification in dual averaging for regularized stochastic online learning

zbMATH Open1432.68392MaRDI QIDQ5405171FDOQ5405171

Authors: Sangkyun Lee, Stephen J. Wright 

Publication date: 1 April 2014

Full work available at URL: http://www.jmlr.org/papers/v13/lee12a.html

Recommendations

• Dual averaging methods for regularized stochastic learning and online optimization
• Adaptive subgradient methods for online learning and stochastic optimization
• Online manifold regularization by dual ascending procedure
• Identifying active manifolds.
• Efficient online and batch learning using forward backward splitting

zbMATH Keywords

regularizationdual averagingmanifold identificationpartly smooth manifold

Mathematics Subject Classification ID

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

Cited In (21)

• Active-set identification with complexity guarantees of an almost cyclic 2-coordinate descent method with Armijo line search
• Distributed Learning with Sparse Communications by Identification
• On variance reduction for stochastic smooth convex optimization with multiplicative noise
• Accelerating inexact successive quadratic approximation for regularized optimization through manifold identification
• A sparsity preserving stochastic gradient methods for sparse regression
• Stochastic algorithms with geometric step decay converge linearly on sharp functions
• Proximal methods avoid active strict saddles of weakly convex functions
• ``Active-set complexity of proximal gradient: how long does it take to find the sparsity pattern?
• Generic minimizing behavior in semialgebraic optimization
• First-order Methods for the Impatient: Support Identification in Finite Time with Convergent Frank--Wolfe Variants
• Asymptotic normality and optimality in nonsmooth stochastic approximation
• Optimality, identifiability, and sensitivity
• Asymptotic properties of dual averaging algorithm for constrained distributed stochastic optimization
• Feature-aware regularization for sparse online learning
• Online manifold regularization by dual ascending procedure
• Dual averaging methods for regularized stochastic learning and online optimization
• Active-set Newton methods and partial smoothness
• Global convergence and acceleration of projection methods for feasibility problems involving union convex sets
• Scalable transfer learning in heterogeneous, dynamic environments
• Asymptotic optimality in stochastic optimization
• Unifying mirror descent and dual averaging

This page was built for publication: Manifold identification in dual averaging for regularized stochastic online learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5405171)