AI RESEARCH
Continuous-Time Dynamics of the Difference-of-Convex Algorithm
arXiv CS.LG
•
ArXi:2604.06926v1 Announce Type: cross We study the continuous-time structure of the difference-of-convex algorithm (DCA) for smooth DC decompositions with a strongly convex component. In dual coordinates, classical DCA is exactly the full-step explicit Euler discretization of a nonlinear autonomous system. This viewpoint motivates a damped DCA scheme, which is also a Bregman-regularized DCA variant, and whose vanishing-step limit yields a Hessian-Riemannian gradient flow generated by the convex part of the decomposition.