DCA-BPCG-WS-ES, a Frank-Wolfe variant with warm-starting and adaptive early stopping, solves constrained DC problems with orders of magnitude fewer linear oracle calls than prior FW-based DCA variants.
On the rate of convergence of the difference-of-convex algorithm ( DCA )
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Scalable DC Optimization via Adaptive Frank-Wolfe Algorithms
DCA-BPCG-WS-ES, a Frank-Wolfe variant with warm-starting and adaptive early stopping, solves constrained DC problems with orders of magnitude fewer linear oracle calls than prior FW-based DCA variants.