AI Research

Second-Order KKT Guarantees for Bregman ADMM in Nonconvex and Non-Lipschitz Optimization

Medium Severity Global
Date Occurred Jun 26, 2026 17:52 UTC
Event Type AI Research
Source arXiv
Recorded Jun 29, 2026
Full Description

arXiv: Second-Order KKT Guarantees for Bregman ADMM in Nonconvex and Non-Lipschitz Optimization We analyze Bregman ADMM for nonconvex linearly constrained problems under two-sided relative smoothness, a condition that replaces the standard Lipschitz gradient assumption with a Hessian comparison relative to a Bregman kernel. This setting covers polynomial objectives arising in matrix and tensor models for which a global Lipschitz-gradient constant need not exist. We show that on an invariant open state-space domain, one iteration of Bregman ADMM defines a smooth primal--dual fixed-point map

AI Intelligence Layer
Event Metadata
  • ID #12021
  • Type AI Research
  • Region Global
  • Severity Medium
  • Indexed Jun 29, 2026