How to Induce Regularization in Linear Models: A Guide to Reparametrizing Gradient Flow
MCML Authors
Johannes Maly
Prof. Dr.
Collaborating PI
Abstract
Johannes Maly
Prof. Dr.
Collaborating PI
Abstract
In this work, we analyze the relation between reparametrizations of gradient flow and the induced implicit bias in linear models, which encompass various basic regression tasks. In particular, we study how reparametrization, loss function, and link function influence the convergence behavior and implicit bias of gradient flow. Our results provide conditions under which the implicit bias can be well-described and convergence of the flow is guaranteed. We furthermore show how to use these insights for designing reparametrization functions that lead to specific implicit biases which are closely connected to lp- or trigonometric regularizers.
article CMS26
Advances in Computational Mathematics
52.75. Aug. 2026.Authors
H.-H. Chou • J. Maly • D. StögerLinks
DOIResearch Area
BibTeXKey: CMS26