Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971223451> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2971223451 endingPage "10899" @default.
- W2971223451 startingPage "10889" @default.
- W2971223451 abstract "A crucial assumption in most statistical learning theory is that samples are independently and identically distributed (i.i.d.). However, for many real applications, the i.i.d. assumption does not hold. We consider learning problems in which examples are dependent and their dependency relation is characterized by a graph. To establish algorithm-dependent generalization theory for learning with non-i.i.d. data, we first prove novel McDiarmid-type concentration inequalities for Lipschitz functions of graph-dependent random variables. We show that concentration relies on the forest complexity of the graph, which characterizes the strength of the dependency. We demonstrate that for many types of dependent data, the forest complexity is small and thus implies good concentration. Based on our new inequalities we are able to build stability bounds for learning from graph-dependent data." @default.
- W2971223451 created "2019-09-05" @default.
- W2971223451 creator A5004035173 @default.
- W2971223451 creator A5055723755 @default.
- W2971223451 creator A5075059527 @default.
- W2971223451 creator A5085255441 @default.
- W2971223451 date "2019-01-01" @default.
- W2971223451 modified "2023-10-18" @default.
- W2971223451 title "McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds" @default.
- W2971223451 hasPublicationYear "2019" @default.
- W2971223451 type Work @default.
- W2971223451 sameAs 2971223451 @default.
- W2971223451 citedByCount "3" @default.
- W2971223451 countsByYear W29712234512018 @default.
- W2971223451 countsByYear W29712234512020 @default.
- W2971223451 countsByYear W29712234512021 @default.
- W2971223451 crossrefType "proceedings-article" @default.
- W2971223451 hasAuthorship W2971223451A5004035173 @default.
- W2971223451 hasAuthorship W2971223451A5055723755 @default.
- W2971223451 hasAuthorship W2971223451A5075059527 @default.
- W2971223451 hasAuthorship W2971223451A5085255441 @default.
- W2971223451 hasConcept C105795698 @default.
- W2971223451 hasConcept C112972136 @default.
- W2971223451 hasConcept C118615104 @default.
- W2971223451 hasConcept C119857082 @default.
- W2971223451 hasConcept C122123141 @default.
- W2971223451 hasConcept C132525143 @default.
- W2971223451 hasConcept C134306372 @default.
- W2971223451 hasConcept C141513077 @default.
- W2971223451 hasConcept C154945302 @default.
- W2971223451 hasConcept C177148314 @default.
- W2971223451 hasConcept C18903297 @default.
- W2971223451 hasConcept C19768560 @default.
- W2971223451 hasConcept C202444582 @default.
- W2971223451 hasConcept C22324862 @default.
- W2971223451 hasConcept C2777299769 @default.
- W2971223451 hasConcept C33923547 @default.
- W2971223451 hasConcept C41008148 @default.
- W2971223451 hasConcept C86803240 @default.
- W2971223451 hasConceptScore W2971223451C105795698 @default.
- W2971223451 hasConceptScore W2971223451C112972136 @default.
- W2971223451 hasConceptScore W2971223451C118615104 @default.
- W2971223451 hasConceptScore W2971223451C119857082 @default.
- W2971223451 hasConceptScore W2971223451C122123141 @default.
- W2971223451 hasConceptScore W2971223451C132525143 @default.
- W2971223451 hasConceptScore W2971223451C134306372 @default.
- W2971223451 hasConceptScore W2971223451C141513077 @default.
- W2971223451 hasConceptScore W2971223451C154945302 @default.
- W2971223451 hasConceptScore W2971223451C177148314 @default.
- W2971223451 hasConceptScore W2971223451C18903297 @default.
- W2971223451 hasConceptScore W2971223451C19768560 @default.
- W2971223451 hasConceptScore W2971223451C202444582 @default.
- W2971223451 hasConceptScore W2971223451C22324862 @default.
- W2971223451 hasConceptScore W2971223451C2777299769 @default.
- W2971223451 hasConceptScore W2971223451C33923547 @default.
- W2971223451 hasConceptScore W2971223451C41008148 @default.
- W2971223451 hasConceptScore W2971223451C86803240 @default.
- W2971223451 hasLocation W29712234511 @default.
- W2971223451 hasOpenAccess W2971223451 @default.
- W2971223451 hasPrimaryLocation W29712234511 @default.
- W2971223451 hasRelatedWork W1517291557 @default.
- W2971223451 hasRelatedWork W1555561626 @default.
- W2971223451 hasRelatedWork W1581328919 @default.
- W2971223451 hasRelatedWork W1837490984 @default.
- W2971223451 hasRelatedWork W2131939929 @default.
- W2971223451 hasRelatedWork W2203637285 @default.
- W2971223451 hasRelatedWork W2489515414 @default.
- W2971223451 hasRelatedWork W2590762295 @default.
- W2971223451 hasRelatedWork W2625084459 @default.
- W2971223451 hasRelatedWork W2767252676 @default.
- W2971223451 hasRelatedWork W2892407672 @default.
- W2971223451 hasRelatedWork W2949348566 @default.
- W2971223451 hasRelatedWork W2964297131 @default.
- W2971223451 hasRelatedWork W2971567195 @default.
- W2971223451 hasRelatedWork W2979918807 @default.
- W2971223451 hasRelatedWork W3104533024 @default.
- W2971223451 hasRelatedWork W3158249193 @default.
- W2971223451 hasRelatedWork W3197649144 @default.
- W2971223451 hasRelatedWork W3206825499 @default.
- W2971223451 hasRelatedWork W2271972072 @default.
- W2971223451 hasVolume "32" @default.
- W2971223451 isParatext "false" @default.
- W2971223451 isRetracted "false" @default.
- W2971223451 magId "2971223451" @default.
- W2971223451 workType "article" @default.