Characterizing the implicit bias via a primal-dual analysis

MaRDI QIDQ7028618zbMATH OpenFDO

Authors Ziwei Ji, Matus Telgarsky

Publication date 11 February 2025

Full work available at URL https://proceedings.mlr.press/v132/ji21a.html

Mathematics Subject Classification ID

Numerical methods involving duality (49M29) Computational aspects of data analysis and big data (68T09) Nonlinear programming (90C30) Applications of mathematical programming (90C90)

Cites work

• A decision-theoretic generalization of on-line learning and an application to boosting
• Boosting. Foundations and algorithms.
• Convex Analysis
• Convex analysis and nonlinear optimization. Theory and examples
• scientific article; zbMATH DE number 1667417 (Why is no real title available?)
• Inequalities.
• Introductory lectures on convex optimization. A basic course.
• Logistic regression, AdaBoost and Bregman distances
• Online learning and online convex optimization
• Sublinear optimization for machine learning
• The dynamics of adaboost: cyclic behavior and convergence of margins

Cited in

(1)

• How to induce regularization in linear models: a guide to reparametrizing gradient flow

This page was built for publication: Characterizing the implicit bias via a primal-dual analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7028618)