Standard GNNs fail to recover linear SDP solutions, but a more expressive architecture emulates first-order solvers, achieves lower error on benchmarks, and yields up to 80% speedups when warm-starting solvers.
A novel neural network for nonlinear convex programming.IEEE Transactions on Neural Networks, 15(3):613–621
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On the Expressive Power of GNNs to Solve Linear SDPs
Standard GNNs fail to recover linear SDP solutions, but a more expressive architecture emulates first-order solvers, achieves lower error on benchmarks, and yields up to 80% speedups when warm-starting solvers.