Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217783298> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3217783298 endingPage "425" @default.
- W3217783298 startingPage "410" @default.
- W3217783298 abstract "In many real world applications of machine learning, models have to meet certain domain-based requirements that can be expressed as constraints (for example, safety-critical constraints in autonomous driving systems). Such constraints are often handled by including them in a regularization term, while learning a model. This approach, however, does not guarantee 100% satisfaction of the constraints: it only reduces violations of the constraints on the training set rather than ensuring that the predictions by the model will always adhere to them. In this paper, we present a framework for learning models that provably fulfill the constraints under all circumstances (i.e., also on unseen data). To achieve this, we cast learning as a maximum satisfiability problem, and solve it using a novel SaDe algorithm that combines constraint satisfaction with gradient descent. We compare our method against regularization based baselines on linear models and show that our method is capable of enforcing different types of domain constraints effectively on unseen data, without sacrificing predictive performance." @default.
- W3217783298 created "2021-12-06" @default.
- W3217783298 creator A5019849127 @default.
- W3217783298 creator A5044610449 @default.
- W3217783298 creator A5086906175 @default.
- W3217783298 date "2023-01-01" @default.
- W3217783298 modified "2023-09-27" @default.
- W3217783298 title "SaDe: Learning Models that Provably Satisfy Domain Constraints" @default.
- W3217783298 cites W1480909796 @default.
- W3217783298 cites W1531103278 @default.
- W3217783298 cites W2201744460 @default.
- W3217783298 cites W2543296129 @default.
- W3217783298 cites W2594877703 @default.
- W3217783298 cites W2888390390 @default.
- W3217783298 cites W2901120714 @default.
- W3217783298 cites W2904239671 @default.
- W3217783298 cites W2957311447 @default.
- W3217783298 cites W2963793947 @default.
- W3217783298 cites W3034399847 @default.
- W3217783298 cites W3040858639 @default.
- W3217783298 cites W3162220519 @default.
- W3217783298 cites W3177445980 @default.
- W3217783298 cites W3197110961 @default.
- W3217783298 cites W3209215190 @default.
- W3217783298 cites W4200315417 @default.
- W3217783298 doi "https://doi.org/10.1007/978-3-031-26419-1_25" @default.
- W3217783298 hasPublicationYear "2023" @default.
- W3217783298 type Work @default.
- W3217783298 sameAs 3217783298 @default.
- W3217783298 citedByCount "0" @default.
- W3217783298 crossrefType "book-chapter" @default.
- W3217783298 hasAuthorship W3217783298A5019849127 @default.
- W3217783298 hasAuthorship W3217783298A5044610449 @default.
- W3217783298 hasAuthorship W3217783298A5086906175 @default.
- W3217783298 hasConcept C11413529 @default.
- W3217783298 hasConcept C119857082 @default.
- W3217783298 hasConcept C126255220 @default.
- W3217783298 hasConcept C134306372 @default.
- W3217783298 hasConcept C154945302 @default.
- W3217783298 hasConcept C168773769 @default.
- W3217783298 hasConcept C177264268 @default.
- W3217783298 hasConcept C199360897 @default.
- W3217783298 hasConcept C199622910 @default.
- W3217783298 hasConcept C2524010 @default.
- W3217783298 hasConcept C2776036281 @default.
- W3217783298 hasConcept C2776135515 @default.
- W3217783298 hasConcept C33923547 @default.
- W3217783298 hasConcept C36503486 @default.
- W3217783298 hasConcept C41008148 @default.
- W3217783298 hasConcept C44616089 @default.
- W3217783298 hasConcept C49937458 @default.
- W3217783298 hasConceptScore W3217783298C11413529 @default.
- W3217783298 hasConceptScore W3217783298C119857082 @default.
- W3217783298 hasConceptScore W3217783298C126255220 @default.
- W3217783298 hasConceptScore W3217783298C134306372 @default.
- W3217783298 hasConceptScore W3217783298C154945302 @default.
- W3217783298 hasConceptScore W3217783298C168773769 @default.
- W3217783298 hasConceptScore W3217783298C177264268 @default.
- W3217783298 hasConceptScore W3217783298C199360897 @default.
- W3217783298 hasConceptScore W3217783298C199622910 @default.
- W3217783298 hasConceptScore W3217783298C2524010 @default.
- W3217783298 hasConceptScore W3217783298C2776036281 @default.
- W3217783298 hasConceptScore W3217783298C2776135515 @default.
- W3217783298 hasConceptScore W3217783298C33923547 @default.
- W3217783298 hasConceptScore W3217783298C36503486 @default.
- W3217783298 hasConceptScore W3217783298C41008148 @default.
- W3217783298 hasConceptScore W3217783298C44616089 @default.
- W3217783298 hasConceptScore W3217783298C49937458 @default.
- W3217783298 hasLocation W32177832981 @default.
- W3217783298 hasOpenAccess W3217783298 @default.
- W3217783298 hasPrimaryLocation W32177832981 @default.
- W3217783298 hasRelatedWork W128226163 @default.
- W3217783298 hasRelatedWork W1483619492 @default.
- W3217783298 hasRelatedWork W1515598460 @default.
- W3217783298 hasRelatedWork W1593899949 @default.
- W3217783298 hasRelatedWork W2011875321 @default.
- W3217783298 hasRelatedWork W2121267470 @default.
- W3217783298 hasRelatedWork W2123500285 @default.
- W3217783298 hasRelatedWork W2180856585 @default.
- W3217783298 hasRelatedWork W2386374330 @default.
- W3217783298 hasRelatedWork W783715155 @default.
- W3217783298 isParatext "false" @default.
- W3217783298 isRetracted "false" @default.
- W3217783298 magId "3217783298" @default.
- W3217783298 workType "book-chapter" @default.