On the equivalence of weak learnability and linear separability: new relaxations and efficient boosting algorithms

DOI10.1007/s10994-010-5173-zzbMath1470.68173OpenAlexW2069936846MaRDI QIDQ1959594

Shai Shalev-Shwartz, Yoram Singer

Publication date: 7 October 2010

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

Full work available at URL: https://doi.org/10.1007/s10994-010-5173-z

zbMATH Keywords

minimax theoremboostinglinear separabilitymargin

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

A precise high-dimensional asymptotic theory for boosting and minimum-\(\ell_1\)-norm interpolated classifiers ⋮ Unnamed Item ⋮ No-regret learning for repeated non-cooperative games with lossy bandits

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Convex analysis and nonlinear optimization. Theory and examples.
• A primal-dual perspective of online learning algorithms
• Boosting the margin: a new explanation for the effectiveness of voting methods
• Analysis of boosting algorithms using the smooth margin function
• 10.1162/153244301753683726
• Entropy Regularized LPBoost
• Sequential greedy approximation for certain convex optimization problems
• 10.1162/153244304773936072
• An adaptive version of the boost by majority algorithm
• Logistic regression, AdaBoost and Bregman distances