A two-step multi-task training strategy for MILP solving produces embeddings that match specialized models in-distribution and generalize better on larger instances and new tasks.
INFORMS Journal on Computing29(1), 185–195 (2017)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-task Representation Learning for Mixed Integer Linear Programming
A two-step multi-task training strategy for MILP solving produces embeddings that match specialized models in-distribution and generalize better on larger instances and new tasks.