The Multi-Block DC class admits polynomial-size DC decompositions for problems that require exponential size under standard DC programming and supplies explicit constructive formulations for deep ReLU networks together with convergent batch and stochastic algorithms.
Journal of Optimization Theory and Applications179(1), 103–126 (2018)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
DCA corresponds to Euler discretization of a Bregman gradient flow, with a damped version providing monotone descent, global linear rates under metric DC-PL, and local exponential convergence near nondegenerate minima.
citing papers explorer
-
The Multi-Block DC Function Class: Theory, Algorithms, and Applications
The Multi-Block DC class admits polynomial-size DC decompositions for problems that require exponential size under standard DC programming and supplies explicit constructive formulations for deep ReLU networks together with convergent batch and stochastic algorithms.
-
Continuous-Time Dynamics of the Difference-of-Convex Algorithm
DCA corresponds to Euler discretization of a Bregman gradient flow, with a damped version providing monotone descent, global linear rates under metric DC-PL, and local exponential convergence near nondegenerate minima.