The impossibility of parallelizing boosting

MaRDI QIDQ7017092zbMATH OpenFDO

Authors Amin Karbasi, Kasper Green Larsen

Publication date 6 March 2025

Full work available at URL https://proceedings.mlr.press/v237/karbasi24a.html

zbMATH Keywords

boostingparallelizationweak-to-strong learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Parallel algorithms in computer science (68W10)

Cites work

• A decision-theoretic generalization of on-line learning and an application to boosting
• Boosting a weak learning algorithm by majority
• Boosting in the presence of noise
• Boosting simple learners
• Boosting the margin: a new explanation for the effectiveness of voting methods
• Boosting using branching programs
• Cryptographic limitations on learning Boolean formulae and finite automata
• Greedy function approximation: A gradient boosting machine.
• scientific article; zbMATH DE number 6378047 (Why is no real title available?)
• Improved bounds on the sample complexity of learning
• Learning Theory
• On the doubt about margin explanation of boosting
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Prediction Games and Arcing Algorithms
• Probability Inequalities for Sums of Bounded Random Variables
• Sharper bounds for Gaussian and empirical processes
• The Distribution of Rademacher Sums
• Understanding machine learning. From theory to algorithms

This page was built for publication: The impossibility of parallelizing boosting

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7017092)