Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034431327> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3034431327 endingPage "144" @default.
- W3034431327 startingPage "134" @default.
- W3034431327 abstract "Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields. Recently, deep reinforcement learning (DRL) frameworks have gained considerable attention as a new approach: they can automate the design of a solver while relying less on sophisticated domain knowledge of the target problem. However, the existing DRL solvers determine the solution using a number of stages proportional to the number of elements in the solution, which severely limits their applicability to large-scale graphs. In this paper, we seek to resolve this issue by proposing a novel DRL scheme, coined learning what to defer (LwD), where the agent adaptively shrinks or stretch the number of stages by learning to distribute the element-wise decisions of the solution at each stage. We apply the proposed framework to the maximum independent set (MIS) problem, and demonstrate its significant improvement over the current state-of-the-art DRL scheme. We also show that LwD can outperform the conventional MIS solvers on large-scale graphs having millions of vertices, under a limited time budget." @default.
- W3034431327 created "2020-06-19" @default.
- W3034431327 creator A5009323476 @default.
- W3034431327 creator A5035397475 @default.
- W3034431327 creator A5035865220 @default.
- W3034431327 date "2020-07-12" @default.
- W3034431327 modified "2023-09-24" @default.
- W3034431327 title "Learning What to Defer for Maximum Independent Sets" @default.
- W3034431327 hasPublicationYear "2020" @default.
- W3034431327 type Work @default.
- W3034431327 sameAs 3034431327 @default.
- W3034431327 citedByCount "3" @default.
- W3034431327 countsByYear W30344313272021 @default.
- W3034431327 crossrefType "proceedings-article" @default.
- W3034431327 hasAuthorship W3034431327A5009323476 @default.
- W3034431327 hasAuthorship W3034431327A5035397475 @default.
- W3034431327 hasAuthorship W3034431327A5035865220 @default.
- W3034431327 hasConcept C121332964 @default.
- W3034431327 hasConcept C126255220 @default.
- W3034431327 hasConcept C134306372 @default.
- W3034431327 hasConcept C154945302 @default.
- W3034431327 hasConcept C177264268 @default.
- W3034431327 hasConcept C199360897 @default.
- W3034431327 hasConcept C2778755073 @default.
- W3034431327 hasConcept C2778770139 @default.
- W3034431327 hasConcept C33923547 @default.
- W3034431327 hasConcept C36503486 @default.
- W3034431327 hasConcept C41008148 @default.
- W3034431327 hasConcept C62520636 @default.
- W3034431327 hasConcept C77618280 @default.
- W3034431327 hasConcept C80444323 @default.
- W3034431327 hasConcept C97541855 @default.
- W3034431327 hasConceptScore W3034431327C121332964 @default.
- W3034431327 hasConceptScore W3034431327C126255220 @default.
- W3034431327 hasConceptScore W3034431327C134306372 @default.
- W3034431327 hasConceptScore W3034431327C154945302 @default.
- W3034431327 hasConceptScore W3034431327C177264268 @default.
- W3034431327 hasConceptScore W3034431327C199360897 @default.
- W3034431327 hasConceptScore W3034431327C2778755073 @default.
- W3034431327 hasConceptScore W3034431327C2778770139 @default.
- W3034431327 hasConceptScore W3034431327C33923547 @default.
- W3034431327 hasConceptScore W3034431327C36503486 @default.
- W3034431327 hasConceptScore W3034431327C41008148 @default.
- W3034431327 hasConceptScore W3034431327C62520636 @default.
- W3034431327 hasConceptScore W3034431327C77618280 @default.
- W3034431327 hasConceptScore W3034431327C80444323 @default.
- W3034431327 hasConceptScore W3034431327C97541855 @default.
- W3034431327 hasLocation W30344313271 @default.
- W3034431327 hasOpenAccess W3034431327 @default.
- W3034431327 hasPrimaryLocation W30344313271 @default.
- W3034431327 hasRelatedWork W1489298886 @default.
- W3034431327 hasRelatedWork W2277493977 @default.
- W3034431327 hasRelatedWork W268427563 @default.
- W3034431327 hasRelatedWork W2766307072 @default.
- W3034431327 hasRelatedWork W2788928868 @default.
- W3034431327 hasRelatedWork W2890695258 @default.
- W3034431327 hasRelatedWork W2904317054 @default.
- W3034431327 hasRelatedWork W2922429874 @default.
- W3034431327 hasRelatedWork W2944551240 @default.
- W3034431327 hasRelatedWork W2950369509 @default.
- W3034431327 hasRelatedWork W2971799085 @default.
- W3034431327 hasRelatedWork W2989628739 @default.
- W3034431327 hasRelatedWork W2990678853 @default.
- W3034431327 hasRelatedWork W3034867503 @default.
- W3034431327 hasRelatedWork W3036460062 @default.
- W3034431327 hasRelatedWork W3126262302 @default.
- W3034431327 hasRelatedWork W3134556739 @default.
- W3034431327 hasRelatedWork W3155153111 @default.
- W3034431327 hasRelatedWork W3199018259 @default.
- W3034431327 hasRelatedWork W86291329 @default.
- W3034431327 hasVolume "1" @default.
- W3034431327 isParatext "false" @default.
- W3034431327 isRetracted "false" @default.
- W3034431327 magId "3034431327" @default.
- W3034431327 workType "article" @default.