Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286909736> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4286909736 abstract "In contrast to single-objective optimization (SOO), multi-objective optimization (MOO) requires an optimizer to find the Pareto frontier, a subset of feasible solutions that are not dominated by other feasible solutions. In this paper, we propose LaMOO, a novel multi-objective optimizer that learns a model from observed samples to partition the search space and then focus on promising regions that are likely to contain a subset of the Pareto frontier. The partitioning is based on the dominance number, which measures how close a data point is to the Pareto frontier among existing samples. To account for possible partition errors due to limited samples and model mismatch, we leverage Monte Carlo Tree Search (MCTS) to exploit promising regions while exploring suboptimal regions that may turn out to contain good solutions later. Theoretically, we prove the efficacy of learning space partitioning via LaMOO under certain assumptions. Empirically, on the HyperVolume (HV) benchmark, a popular MOO metric, LaMOO substantially outperforms strong baselines on multiple real-world MOO tasks, by up to 225% in sample efficiency for neural architecture search on Nasbench201, and up to 10% for molecular design." @default.
- W4286909736 created "2022-07-25" @default.
- W4286909736 creator A5025376043 @default.
- W4286909736 creator A5027398178 @default.
- W4286909736 creator A5030604333 @default.
- W4286909736 creator A5060834723 @default.
- W4286909736 creator A5063040669 @default.
- W4286909736 creator A5084821923 @default.
- W4286909736 date "2021-10-06" @default.
- W4286909736 modified "2023-10-16" @default.
- W4286909736 title "Multi-objective Optimization by Learning Space Partitions" @default.
- W4286909736 hasPublicationYear "2021" @default.
- W4286909736 type Work @default.
- W4286909736 citedByCount "0" @default.
- W4286909736 crossrefType "posted-content" @default.
- W4286909736 hasAuthorship W4286909736A5025376043 @default.
- W4286909736 hasAuthorship W4286909736A5027398178 @default.
- W4286909736 hasAuthorship W4286909736A5030604333 @default.
- W4286909736 hasAuthorship W4286909736A5060834723 @default.
- W4286909736 hasAuthorship W4286909736A5063040669 @default.
- W4286909736 hasAuthorship W4286909736A5084821923 @default.
- W4286909736 hasBestOaLocation W42869097361 @default.
- W4286909736 hasConcept C105795698 @default.
- W4286909736 hasConcept C114614502 @default.
- W4286909736 hasConcept C119857082 @default.
- W4286909736 hasConcept C126255220 @default.
- W4286909736 hasConcept C127413603 @default.
- W4286909736 hasConcept C13280743 @default.
- W4286909736 hasConcept C137635306 @default.
- W4286909736 hasConcept C153083717 @default.
- W4286909736 hasConcept C165696696 @default.
- W4286909736 hasConcept C176217482 @default.
- W4286909736 hasConcept C185798385 @default.
- W4286909736 hasConcept C19499675 @default.
- W4286909736 hasConcept C205649164 @default.
- W4286909736 hasConcept C21547014 @default.
- W4286909736 hasConcept C33923547 @default.
- W4286909736 hasConcept C38652104 @default.
- W4286909736 hasConcept C41008148 @default.
- W4286909736 hasConcept C42812 @default.
- W4286909736 hasConcept C68781425 @default.
- W4286909736 hasConceptScore W4286909736C105795698 @default.
- W4286909736 hasConceptScore W4286909736C114614502 @default.
- W4286909736 hasConceptScore W4286909736C119857082 @default.
- W4286909736 hasConceptScore W4286909736C126255220 @default.
- W4286909736 hasConceptScore W4286909736C127413603 @default.
- W4286909736 hasConceptScore W4286909736C13280743 @default.
- W4286909736 hasConceptScore W4286909736C137635306 @default.
- W4286909736 hasConceptScore W4286909736C153083717 @default.
- W4286909736 hasConceptScore W4286909736C165696696 @default.
- W4286909736 hasConceptScore W4286909736C176217482 @default.
- W4286909736 hasConceptScore W4286909736C185798385 @default.
- W4286909736 hasConceptScore W4286909736C19499675 @default.
- W4286909736 hasConceptScore W4286909736C205649164 @default.
- W4286909736 hasConceptScore W4286909736C21547014 @default.
- W4286909736 hasConceptScore W4286909736C33923547 @default.
- W4286909736 hasConceptScore W4286909736C38652104 @default.
- W4286909736 hasConceptScore W4286909736C41008148 @default.
- W4286909736 hasConceptScore W4286909736C42812 @default.
- W4286909736 hasConceptScore W4286909736C68781425 @default.
- W4286909736 hasLocation W42869097361 @default.
- W4286909736 hasOpenAccess W4286909736 @default.
- W4286909736 hasPrimaryLocation W42869097361 @default.
- W4286909736 hasRelatedWork W1137530 @default.
- W4286909736 hasRelatedWork W11553712 @default.
- W4286909736 hasRelatedWork W11997848 @default.
- W4286909736 hasRelatedWork W13152143 @default.
- W4286909736 hasRelatedWork W14372312 @default.
- W4286909736 hasRelatedWork W2463997 @default.
- W4286909736 hasRelatedWork W3112368 @default.
- W4286909736 hasRelatedWork W7198858 @default.
- W4286909736 hasRelatedWork W9544208 @default.
- W4286909736 hasRelatedWork W9835653 @default.
- W4286909736 isParatext "false" @default.
- W4286909736 isRetracted "false" @default.
- W4286909736 workType "article" @default.