Adaptive and optimal online linear regression on \(\ell^1\)-balls

DOI10.1016/j.tcs.2013.09.024zbMath1352.62108OpenAlexW2963812988MaRDI QIDQ391734

Jia Yuan Yu, Sébastien Gerchinovitz

Publication date: 13 January 2014

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2013.09.024

zbMATH Keywords

minimax regretonline learningadaptive algorithmslinear regression

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27)

Cites Work

• Unnamed Item
• Exponentiated gradient versus gradient descent for linear predictors
• The robustness of the \(p\)-norm algorithms
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Aggregating regression procedures to improve performance
• Adaptive and self-confident on-line learning algorithms
• Analysis of two gradient-based algorithms for on-line regression
• Improved second-order bounds for prediction with expert advice
• Trading Accuracy for Sparsity in Optimization Problems with Sparsity Constraints
• Minimizing Regret With Label Efficient Prediction
• Sequential Procedures for Aggregating Arbitrary Estimators of a Conditional Mean
• Competitive On-line Statistics
• Minimax Rates of Estimation for High-Dimensional Linear Regression Over $\ell_q$-Balls
• Learning Theory and Kernel Machines
• Prediction, Learning, and Games
• Gaussian model selection
• Relative loss bounds for on-line density estimation with the exponential family of distributions

This page was built for publication: Adaptive and optimal online linear regression on \(\ell^1\)-balls