Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper analyzes the continuous-time dynamics of the Difference-of-Convex Algorithm (DCA) by showing that the classical DCA is an explicit Euler discretization of a nonlinear autonomous system in dual coordinates. Based on this viewpoint, the authors propose a damped DCA scheme and its vanishing-step limit, a Hessian-Riemannian gradient flow. They then establish convergence guarantees for both the damped scheme and the limiting flow, including monotone descent, asymptotic criticality, and convergence rates under various conditions.
DCA's convergence rate and behavior are highly dependent on the specific DC decomposition used, offering a geometric criterion for assessing decomposition quality and linking DCA with Bregman geometry.
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. For the damped scheme we prove monotone descent, asymptotic criticality, Kurdyka-Lojasiewicz convergence under boundedness, and a global linear rate under a metric DC-PL inequality. For the limiting flow we establish an exact energy identity, asymptotic criticality of bounded trajectories, explicit global rates under metric relative error bounds, finite-length and single-point convergence under a Kurdyka-Lojasiewicz hypothesis, and local exponential convergence near nondegenerate local minima. The analysis also reveals a global-local tradeoff: the half-relaxed scheme gives the best provable global guarantee in our framework, while the full-step scheme is locally fastest near a nondegenerate minimum. Finally, we show that different DC decompositions of the same objective induce different continuous dynamics through the metric generated by the convex component, providing a geometric criterion for decomposition quality and linking DCA with Bregman geometry.