Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 28, 2026Advances in Computational MathematicsOpen Access

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

View Full Paper
Ask AI
Bookmark
Share

Authors

HCHung-Hsu ChouJMJohannes MalyDSDominik Stöger

Discussion

Loading...

Member takes

Overview

Theoretical analysis demonstrates how reparametrizing gradient flow induces specific implicit biases in linear models, suggesting new methods to design targeted algorithmic regularizers.

Key Points

  • Characterize the mathematical relationship between gradient flow reparametrizations and induced implicit bias across linear models.
  • Analyzed the joint influence of model reparametrizations, loss functions, and link functions on gradient flow dynamics.
  • Derived formal conditions governing convergence guarantees and explicit characterizations of implicit bias.
  • Established precise theoretical conditions under which gradient flow convergence is guaranteed and its implicit bias can be analytically described.
  • Demonstrated the systematic design of reparametrizations that induce targeted implicit regularizers, specifically connecting them to lp and trigonometric penalty functions.

Cite This Study

Chou et al. (2026) studied this question.

synapsesocial.com/papers/6a914631d15324a1df3a9930https://doi.org/10.1007/s10444-026-10350-3
View Full Paper
Ask AI
Bookmark
Share