A large-sample theory for infinitesimal gradient boosting

DOI10.3150/23-BEJ1657MaRDI QIDQ6565306zbMATH OpenFDO

Authors Clément Dombry, Jean-Jil Duchamps

Publication date 2 July 2024

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3150/23-BEJ1657

zbMATH Keywords

gradient boostinglarge sample theorysoftmax gradient tree

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Recommendations

• Some theory for generalized boosting algorithms
• Population theory for boosting ensembles.
• Stochastic gradient boosting.
• Accelerated gradient boosting
• Greedy function approximation: A gradient boosting machine.

Cites work

• 10.1162/1532443041424319
• Analysis of stochastic gradient descent in continuous time
• Boosting with early stopping: convergence and consistency
• Bridging the gap between constant step size stochastic gradient descent and Markov chains
• Consistency of random forests
• Extremely randomized trees
• Greedy function approximation: A gradient boosting machine.
• scientific article; zbMATH DE number 3860199 (Why is no real title available?)
• On the Bayes-risk consistency of regularized boosting methods.
• Population theory for boosting ensembles.
• Probability. Theory and examples.
• Process consistency for AdaBoost.
• The AdaBoost flow
• The Elements of Statistical Learning
• Weak convergence and empirical processes. With applications to statistics

This page was built for publication: A large-sample theory for infinitesimal gradient boosting

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6565306)