A 4-layer network derived from a gradient-modified Douglas-Rachford algorithm predicts warm starts that reduce SCS iterations by up to 50% and total solve time by up to 40% on convex QP benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Solving Quadratic Programs via Deep Unrolled Douglas-Rachford Splitting
A 4-layer network derived from a gradient-modified Douglas-Rachford algorithm predicts warm starts that reduce SCS iterations by up to 50% and total solve time by up to 40% on convex QP benchmarks.