A primal-dual perspective of online learning algorithms

DOI10.1007/s10994-007-5014-xzbMath1470.68172OpenAlexW2074586650MaRDI QIDQ1009218

Yoram Singer, Shai Shalev-Shwartz

Publication date: 31 March 2009

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-007-5014-x

zbMATH Keywords

dualityonline learningregret boundsmistake bounds

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Optimality conditions and duality in mathematical programming (90C46) Online algorithms; streaming algorithms (68W27)

Related Items (15)

Competitive online algorithms for resource allocation over the positive semidefinite cone ⋮ Online Learning with (Multiple) Kernels: A Review ⋮ Feature-aware regularization for sparse online learning ⋮ Regrets of proximal method of multipliers for online non-convex optimization with long term constraints ⋮ Adaptive echo state network with a recursive inverse-free weight update algorithm ⋮ Online multiple kernel classification ⋮ Open issues and recent advances in DC programming and DCA ⋮ Dynamical memory control based on projection technique for online regression ⋮ On the equivalence of weak learnability and linear separability: new relaxations and efficient boosting algorithms ⋮ Online Learning Based on Online DCA and Application to Online Classification ⋮ Robust \(H_\infty\) control for nonlinear uncertain switched descriptor systems with time delay and nonlinear input: a sliding mode approach ⋮ A generalized online mirror descent with applications to classification and regression ⋮ Unnamed Item ⋮ Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent ⋮ Unnamed Item

Uses Software

• Forgetron

Cites Work

• Exponentiated gradient versus gradient descent for linear predictors
• The robustness of the \(p\)-norm algorithms
• 10.1162/15324430260185600
• The Forgetron: A Kernel-Based Perceptron on a Budget
• On the Generalization Ability of On-Line Learning Algorithms
• Competitive On-line Statistics
• A Second-Order Perceptron Algorithm
• Online Learning with Kernels
• Convex Analysis
• General convergence results for linear discriminant updates
• Relative loss bounds for on-line density estimation with the exponential family of distributions
• Relative loss bounds for multidimensional regression problems
• The relaxed online maximum margin algorithm
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: A primal-dual perspective of online learning algorithms