Matches in SemOpenAlex for { <https://semopenalex.org/work/W4360982506> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4360982506 endingPage "392" @default.
- W4360982506 startingPage "377" @default.
- W4360982506 abstract "Deriving a good variable selection strategy in branch-and-bound is essential for the efficiency of modern mixed-integer programming (MIP) solvers. With MIP branching data collected during the previous solution process, learning to branch methods have recently become superior over heuristics. As branch-and-bound is naturally a sequential decision making task, one should learn to optimize the utility of the whole MIP solving process instead of being myopic on each step. In this work, we formulate learning to branch as an offline reinforcement learning (RL) problem, and propose a long-sighted hybrid search scheme to construct the offline MIP dataset, which values the long-term utilities of branching decisions. During the policy training phase, we deploy a ranking-based reward assignment scheme to distinguish the promising samples from the long-term or short-term view, and train the branching model named Branch Ranking via offline policy learning. Experiments on synthetic MIP benchmarks and real-world tasks demonstrate that Branch Ranking is more efficient and robust, and can better generalize to large scales of MIP instances compared to the widely used heuristics and state-of-the-art learning-based branching models." @default.
- W4360982506 created "2023-03-30" @default.
- W4360982506 creator A5001571390 @default.
- W4360982506 creator A5009553397 @default.
- W4360982506 creator A5026553094 @default.
- W4360982506 creator A5031170152 @default.
- W4360982506 creator A5042241049 @default.
- W4360982506 creator A5044403966 @default.
- W4360982506 creator A5047509839 @default.
- W4360982506 creator A5078949174 @default.
- W4360982506 creator A5087578121 @default.
- W4360982506 creator A5090720315 @default.
- W4360982506 date "2023-01-01" @default.
- W4360982506 modified "2023-09-27" @default.
- W4360982506 title "Branch Ranking for Efficient Mixed-Integer Programming via Offline Ranking-Based Policy Learning" @default.
- W4360982506 cites W1534573459 @default.
- W4360982506 cites W2031513260 @default.
- W4360982506 cites W2047221353 @default.
- W4360982506 cites W2089368295 @default.
- W4360982506 cites W2277678953 @default.
- W4360982506 cites W2576311753 @default.
- W4360982506 cites W3047863327 @default.
- W4360982506 cites W3090460193 @default.
- W4360982506 cites W3173319990 @default.
- W4360982506 doi "https://doi.org/10.1007/978-3-031-26419-1_23" @default.
- W4360982506 hasPublicationYear "2023" @default.
- W4360982506 type Work @default.
- W4360982506 citedByCount "0" @default.
- W4360982506 crossrefType "book-chapter" @default.
- W4360982506 hasAuthorship W4360982506A5001571390 @default.
- W4360982506 hasAuthorship W4360982506A5009553397 @default.
- W4360982506 hasAuthorship W4360982506A5026553094 @default.
- W4360982506 hasAuthorship W4360982506A5031170152 @default.
- W4360982506 hasAuthorship W4360982506A5042241049 @default.
- W4360982506 hasAuthorship W4360982506A5044403966 @default.
- W4360982506 hasAuthorship W4360982506A5047509839 @default.
- W4360982506 hasAuthorship W4360982506A5078949174 @default.
- W4360982506 hasAuthorship W4360982506A5087578121 @default.
- W4360982506 hasAuthorship W4360982506A5090720315 @default.
- W4360982506 hasConcept C111919701 @default.
- W4360982506 hasConcept C11413529 @default.
- W4360982506 hasConcept C119857082 @default.
- W4360982506 hasConcept C126255220 @default.
- W4360982506 hasConcept C127705205 @default.
- W4360982506 hasConcept C154945302 @default.
- W4360982506 hasConcept C189430467 @default.
- W4360982506 hasConcept C33923547 @default.
- W4360982506 hasConcept C41008148 @default.
- W4360982506 hasConcept C56086750 @default.
- W4360982506 hasConcept C86037889 @default.
- W4360982506 hasConcept C93693863 @default.
- W4360982506 hasConcept C97541855 @default.
- W4360982506 hasConceptScore W4360982506C111919701 @default.
- W4360982506 hasConceptScore W4360982506C11413529 @default.
- W4360982506 hasConceptScore W4360982506C119857082 @default.
- W4360982506 hasConceptScore W4360982506C126255220 @default.
- W4360982506 hasConceptScore W4360982506C127705205 @default.
- W4360982506 hasConceptScore W4360982506C154945302 @default.
- W4360982506 hasConceptScore W4360982506C189430467 @default.
- W4360982506 hasConceptScore W4360982506C33923547 @default.
- W4360982506 hasConceptScore W4360982506C41008148 @default.
- W4360982506 hasConceptScore W4360982506C56086750 @default.
- W4360982506 hasConceptScore W4360982506C86037889 @default.
- W4360982506 hasConceptScore W4360982506C93693863 @default.
- W4360982506 hasConceptScore W4360982506C97541855 @default.
- W4360982506 hasLocation W43609825061 @default.
- W4360982506 hasOpenAccess W4360982506 @default.
- W4360982506 hasPrimaryLocation W43609825061 @default.
- W4360982506 hasRelatedWork W1968110187 @default.
- W4360982506 hasRelatedWork W1992729760 @default.
- W4360982506 hasRelatedWork W2037603740 @default.
- W4360982506 hasRelatedWork W2154007187 @default.
- W4360982506 hasRelatedWork W2166669554 @default.
- W4360982506 hasRelatedWork W2379162478 @default.
- W4360982506 hasRelatedWork W2579667758 @default.
- W4360982506 hasRelatedWork W3139941598 @default.
- W4360982506 hasRelatedWork W637971315 @default.
- W4360982506 hasRelatedWork W96560802 @default.
- W4360982506 isParatext "false" @default.
- W4360982506 isRetracted "false" @default.
- W4360982506 workType "book-chapter" @default.