A lightweight neural dual predictor accelerates exact LAP solvers by over 2x on synthetic data and 1.25-1.5x on real MOT and LPT tasks while preserving full optimality and scaling to N=16384.
Binary Search with Distributional Predictions , booktitle =
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
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts
A lightweight neural dual predictor accelerates exact LAP solvers by over 2x on synthetic data and 1.25-1.5x on real MOT and LPT tasks while preserving full optimality and scaling to N=16384.