Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971567195> ?p ?o ?g. }
- W2971567195 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.
- W2971567195 created "2019-09-12" @default.
- W2971567195 creator A5004035173 @default.
- W2971567195 creator A5055723755 @default.
- W2971567195 creator A5075059527 @default.
- W2971567195 creator A5085255441 @default.
- W2971567195 date "2019-09-05" @default.
- W2971567195 modified "2023-09-23" @default.
- W2971567195 title "McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds" @default.
- W2971567195 cites W1495120270 @default.
- W2971567195 cites W1510966913 @default.
- W2971567195 cites W1804540308 @default.
- W2971567195 cites W1837490984 @default.
- W2971567195 cites W1966733153 @default.
- W2971567195 cites W1980362252 @default.
- W2971567195 cites W1988370192 @default.
- W2971567195 cites W2020703529 @default.
- W2971567195 cites W2028226037 @default.
- W2971567195 cites W2031173376 @default.
- W2971567195 cites W2055186664 @default.
- W2971567195 cites W2056871913 @default.
- W2971567195 cites W2060534685 @default.
- W2971567195 cites W2075672181 @default.
- W2971567195 cites W2078750760 @default.
- W2971567195 cites W2078894510 @default.
- W2971567195 cites W2104290726 @default.
- W2971567195 cites W2132353975 @default.
- W2971567195 cites W2132664995 @default.
- W2971567195 cites W2137207609 @default.
- W2971567195 cites W2138263042 @default.
- W2971567195 cites W2139338362 @default.
- W2971567195 cites W2141732327 @default.
- W2971567195 cites W2160158327 @default.
- W2971567195 cites W2223869665 @default.
- W2971567195 cites W2253472364 @default.
- W2971567195 cites W2528961511 @default.
- W2971567195 cites W2538377176 @default.
- W2971567195 cites W2736970300 @default.
- W2971567195 cites W2899489514 @default.
- W2971567195 cites W2963011376 @default.
- W2971567195 cites W2963750582 @default.
- W2971567195 cites W2964020133 @default.
- W2971567195 cites W2964215083 @default.
- W2971567195 cites W2966252424 @default.
- W2971567195 cites W2989661724 @default.
- W2971567195 cites W78433401 @default.
- W2971567195 cites W165498608 @default.
- W2971567195 cites W2804900785 @default.
- W2971567195 hasPublicationYear "2019" @default.
- W2971567195 type Work @default.
- W2971567195 sameAs 2971567195 @default.
- W2971567195 citedByCount "0" @default.
- W2971567195 crossrefType "posted-content" @default.
- W2971567195 hasAuthorship W2971567195A5004035173 @default.
- W2971567195 hasAuthorship W2971567195A5055723755 @default.
- W2971567195 hasAuthorship W2971567195A5075059527 @default.
- W2971567195 hasAuthorship W2971567195A5085255441 @default.
- W2971567195 hasConcept C105795698 @default.
- W2971567195 hasConcept C112972136 @default.
- W2971567195 hasConcept C118615104 @default.
- W2971567195 hasConcept C119857082 @default.
- W2971567195 hasConcept C122123141 @default.
- W2971567195 hasConcept C132525143 @default.
- W2971567195 hasConcept C134306372 @default.
- W2971567195 hasConcept C141513077 @default.
- W2971567195 hasConcept C154945302 @default.
- W2971567195 hasConcept C177148314 @default.
- W2971567195 hasConcept C18903297 @default.
- W2971567195 hasConcept C19768560 @default.
- W2971567195 hasConcept C202444582 @default.
- W2971567195 hasConcept C22324862 @default.
- W2971567195 hasConcept C2777299769 @default.
- W2971567195 hasConcept C2982736386 @default.
- W2971567195 hasConcept C33923547 @default.
- W2971567195 hasConcept C41008148 @default.
- W2971567195 hasConcept C86803240 @default.
- W2971567195 hasConceptScore W2971567195C105795698 @default.
- W2971567195 hasConceptScore W2971567195C112972136 @default.
- W2971567195 hasConceptScore W2971567195C118615104 @default.
- W2971567195 hasConceptScore W2971567195C119857082 @default.
- W2971567195 hasConceptScore W2971567195C122123141 @default.
- W2971567195 hasConceptScore W2971567195C132525143 @default.
- W2971567195 hasConceptScore W2971567195C134306372 @default.
- W2971567195 hasConceptScore W2971567195C141513077 @default.
- W2971567195 hasConceptScore W2971567195C154945302 @default.
- W2971567195 hasConceptScore W2971567195C177148314 @default.
- W2971567195 hasConceptScore W2971567195C18903297 @default.
- W2971567195 hasConceptScore W2971567195C19768560 @default.
- W2971567195 hasConceptScore W2971567195C202444582 @default.
- W2971567195 hasConceptScore W2971567195C22324862 @default.
- W2971567195 hasConceptScore W2971567195C2777299769 @default.
- W2971567195 hasConceptScore W2971567195C2982736386 @default.
- W2971567195 hasConceptScore W2971567195C33923547 @default.
- W2971567195 hasConceptScore W2971567195C41008148 @default.
- W2971567195 hasConceptScore W2971567195C86803240 @default.
- W2971567195 hasOpenAccess W2971567195 @default.
- W2971567195 hasRelatedWork W1517291557 @default.
- W2971567195 hasRelatedWork W1555561626 @default.
- W2971567195 hasRelatedWork W1581328919 @default.
- W2971567195 hasRelatedWork W1837490984 @default.