A primal sub-gradient method for structured classification with the averaged sum loss

DOI10.2478/AMCS-2014-0067MaRDI QIDQ2018420zbMATH OpenOpenAlexFDO

Authors Dejan Mančev, Branimir Todorović

Publication date 14 April 2015

Published in International Journal of Applied Mathematics and Computer Science (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported

Full work available at URL https://doi.org/10.2478/amcs-2014-0067

zbMATH Keywords

sequence labelingstructured classificationsub-gradient methodssupport vector machines

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Pegasos: primal estimated sub-gradient solver for SVM
• A sequential dual method for the structured ramp loss minimization
• Cutting-plane training of structural SVMs
• Structured prediction, dual extragradient and Bregman projections
• Adaptive subgradient methods for online learning and stochastic optimization

Cites work

• Cutting-plane training of structural SVMs
• Exponentiated gradient algorithms for conditional random fields and max-margin Markov networks
• scientific article; zbMATH DE number 5957338 (Why is no real title available?)
• scientific article; zbMATH DE number 5547839 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• Large margin methods for structured and interdependent output variables
• Pegasos: primal estimated sub-gradient solver for SVM
• Robust Stochastic Approximation Approach to Stochastic Programming
• Structured Learning and Prediction in Computer Vision

Cited in

(1)

• A sequential dual method for the structured ramp loss minimization

Describes a project that uses

Uses Software

• Pegasos

This page was built for publication: A primal sub-gradient method for structured classification with the averaged sum loss

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2018420)