Periodic step-size adaptation in second-order gradient descent for single-pass on-line structured learning

DOI10.1007/s10994-009-5142-6zbMath1470.68116OpenAlexW2102547221MaRDI QIDQ1959528

Chun-Nan Hsu, Han-Shen Huang, Yu-Ming Chang, Yuh-Jye Lee

Publication date: 7 October 2010

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

Full work available at URL: https://doi.org/10.1007/s10994-009-5142-6

zbMATH Keywords

online learningstochastic gradient descentconvolutional neural networksconditional random fieldssequence labeling

Mathematics Subject Classification ID

Random fields; image analysis (62M40) Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15) Online algorithms; streaming algorithms (68W27)

Related Items (1)

ACCELERATING GENERALIZED ITERATIVE SCALING BASED ON STAGGERED AITKEN METHOD FOR ON-LINE CONDITIONAL RANDOM FIELDS

Uses Software

• SVMlight
• LIBSVM
• Pegasos
• CRF++
• MNIST

Cites Work

• Pegasos: primal estimated sub-gradient solver for SVM
• Statistical analysis of learning dynamics
• On the global and componentwise rates of convergence of the EM algorithm
• On computing the largest fraction of missing information for the EM algorithm and the worst linear function for data augmentation.
• Numerical Optimization
• Introduction to Stochastic Search and Optimization
• On‐line learning for very large data sets
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Periodic step-size adaptation in second-order gradient descent for single-pass on-line structured learning