On Complexity Issues of Online Learning Algorithms

DOI10.1109/TIT.2010.2079010MaRDI QIDQ5281195zbMATH OpenOpenAlexFDO

Authors Yuan Yao

Publication date 27 July 2017

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tit.2010.2079010

Mathematics Subject Classification ID

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

Cited in

(19)

• Logistic classification with varying gaussians
• Online learning for quantile regression and support vector regression
• Convergence of online mirror descent
• Fast and strong convergence of online learning algorithms
• Derivative reproducing properties for kernel methods in learning theory
• Approximation analysis of learning algorithms for support vector regression and quantile regression
• Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
• Convergence of unregularized online learning algorithms
• Can entropy characterize performance of online algorithms?
• Online Pairwise Learning Algorithms
• Parameter learning algorithm for the online data acknowledgment problem
• Conditional quantiles with varying Gaussians
• Optimality of robust online learning
• ERM scheme for quantile regression
• Rates of convergence of randomized Kaczmarz algorithms in Hilbert spaces
• On-line learning and the metrical task system problem
• Learning with varying insensitive loss
• On-line learning in parity machines
• On grouping effect of elastic net

This page was built for publication: On Complexity Issues of Online Learning Algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5281195)