The robustness of the \(p\)-norm algorithms

DOI10.1023/A:1026319107706zbMath1089.68093OpenAlexW1540586255MaRDI QIDQ703062

Claudio Gentile

Publication date: 19 January 2005

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

Full work available at URL: https://doi.org/10.1023/a:1026319107706

zbMATH Keywords

dual normslearning rateloss boundsOn-line learningon-line model selection

Mathematics Subject Classification ID

Nonnumerical algorithms (68W05) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (14)

Applications of regularized least squares to pattern classification ⋮ Possibility theoretic clustering and its preliminary application to large image segmentation ⋮ Adaptive regularization of weight vectors ⋮ Adaptive and optimal online linear regression on \(\ell^1\)-balls ⋮ Variance reduction on general adaptive stochastic mirror descent ⋮ Optimistic optimisation of composite objective with exponentiated update ⋮ Exploiting Cluster-Structure to Predict the Labeling of a Graph ⋮ Online Learning Based on Online DCA and Application to Online Classification ⋮ A generalized online mirror descent with applications to classification and regression ⋮ Tracking the best hyperplane with a simple budget perceptron ⋮ A primal-dual perspective of online learning algorithms ⋮ Learning to assign degrees of belief in relational domains ⋮ Implicit Regularization and Momentum Algorithms in Nonlinearly Parameterized Adaptive Control and Prediction ⋮ Exponential weight approachability, applications to calibration and regret minimization

This page was built for publication: The robustness of the \(p\)-norm algorithms