A new unified method for directional stationary points of non-smooth DC programs with both components possibly non-smooth, plus deterministic and randomized convergence results.
Mathematical Programming169(1), 5–68 (2018)
4 Pith papers cite this work, alongside 350 external citations. Polarity classification is still indexing.
4
Pith papers citing it
350
external citations · OpenAlex
fields
math.OC 4years
2026 4verdicts
UNVERDICTED 4representative 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.
Introduces HOME-DC smoothing for DC functions, derives an inexact first-order oracle, and proposes convergent inexact descent methods with preliminary numerical support on sparse clustering.
RA-DCA applies randomized vertex screening inside DCA iterations for max-structured DC programs and proves that safeguarded accumulation points are directionally stationary with probability one under regularity, active-set consistency, and random-embedding assumptions.
citing papers explorer
-
Finding directional stationary points of DC programs
A new unified method for directional stationary points of non-smooth DC programs with both components possibly non-smooth, plus deterministic and randomized convergence results.
-
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.
-
Difference-of-Convex Optimization via Inexact Smoothing Descent Methods: Difference of High-Order Moreau Envelopes
Introduces HOME-DC smoothing for DC functions, derives an inexact first-order oracle, and proposes convergent inexact descent methods with preliminary numerical support on sparse clustering.
-
RA-DCA: A Randomized Active-Set DCA for Directional Stationarity in Max-Structured DC Programs
RA-DCA applies randomized vertex screening inside DCA iterations for max-structured DC programs and proves that safeguarded accumulation points are directionally stationary with probability one under regularity, active-set consistency, and random-embedding assumptions.