Convergence of Gradient Descent for Minimum Error Entropy Principle in Linear Regression

DOI10.1109/TSP.2016.2612169MaRDI QIDQ4619681zbMATH OpenOpenAlexFDO

Authors Ting Hu, Qiang Wu, Ding-Xuan Zhou

Publication date 7 February 2019

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tsp.2016.2612169

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cited in

(9)

• Fast rates of minimum error entropy with heavy-tailed noise
• Distributed kernel gradient descent algorithm for minimum error entropy principle
• Kernel gradient descent algorithm for information theoretic learning
• Distributed minimum error entropy algorithms
• A Framework of Learning Through Empirical Gain Maximization
• Learning theory of minimum error entropy under weak moment conditions
• Stability and optimization error of stochastic gradient descent for pairwise learning
• Online minimum error entropy algorithm with unbounded sampling
• Robust learning of Huber loss under exponentially strongly mixing sequence

This page was built for publication: Convergence of Gradient Descent for Minimum Error Entropy Principle in Linear Regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4619681)