Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022819384> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3022819384 abstract "Models can be simple for different reasons: because they yield a simple and computationally efficient interpretation of a generic dataset (e.g. in terms of pairwise dependences) - as in statistical learning - or because they capture the essential ingredients of a specific phenomenon - as e.g. in physics - leading to non-trivial falsifiable predictions. In information theory and Bayesian inference, the simplicity of a model is precisely quantified in the stochastic complexity, which measures the number of bits needed to encode its parameters. In order to understand how simple models look like, we study the stochastic complexity of spin models with interactions of arbitrary order. We highlight the existence of invariances with respect to bijections within the space of operators, which allow us to partition the space of all models into equivalence classes, in which models share the same complexity. We thus found that the complexity (or simplicity) of a model is not determined by the order of the interactions, but rather by their mutual arrangements. Models where statistical dependencies are localized on non-overlapping groups of few variables (and that afford predictions on independencies that are easy to falsify) are simple. On the contrary, fully connected pairwise models, which are often used in statistical learning, appear to be highly complex, because of their extended set of interactions." @default.
- W3022819384 created "2020-05-13" @default.
- W3022819384 creator A5007499835 @default.
- W3022819384 creator A5014868427 @default.
- W3022819384 creator A5025728489 @default.
- W3022819384 creator A5051471901 @default.
- W3022819384 creator A5064717998 @default.
- W3022819384 date "2019-03-05" @default.
- W3022819384 modified "2023-09-24" @default.
- W3022819384 title "The Stochastic Complexity of Spin Models: Are Pairwise Models Really Simple?" @default.
- W3022819384 hasPublicationYear "2019" @default.
- W3022819384 type Work @default.
- W3022819384 sameAs 3022819384 @default.
- W3022819384 citedByCount "0" @default.
- W3022819384 crossrefType "journal-article" @default.
- W3022819384 hasAuthorship W3022819384A5007499835 @default.
- W3022819384 hasAuthorship W3022819384A5014868427 @default.
- W3022819384 hasAuthorship W3022819384A5025728489 @default.
- W3022819384 hasAuthorship W3022819384A5051471901 @default.
- W3022819384 hasAuthorship W3022819384A5064717998 @default.
- W3022819384 hasConcept C111472728 @default.
- W3022819384 hasConcept C118615104 @default.
- W3022819384 hasConcept C138885662 @default.
- W3022819384 hasConcept C154945302 @default.
- W3022819384 hasConcept C184898388 @default.
- W3022819384 hasConcept C24424167 @default.
- W3022819384 hasConcept C2776372474 @default.
- W3022819384 hasConcept C2780586882 @default.
- W3022819384 hasConcept C33923547 @default.
- W3022819384 hasConcept C41008148 @default.
- W3022819384 hasConcept C48659774 @default.
- W3022819384 hasConcept C80444323 @default.
- W3022819384 hasConceptScore W3022819384C111472728 @default.
- W3022819384 hasConceptScore W3022819384C118615104 @default.
- W3022819384 hasConceptScore W3022819384C138885662 @default.
- W3022819384 hasConceptScore W3022819384C154945302 @default.
- W3022819384 hasConceptScore W3022819384C184898388 @default.
- W3022819384 hasConceptScore W3022819384C24424167 @default.
- W3022819384 hasConceptScore W3022819384C2776372474 @default.
- W3022819384 hasConceptScore W3022819384C2780586882 @default.
- W3022819384 hasConceptScore W3022819384C33923547 @default.
- W3022819384 hasConceptScore W3022819384C41008148 @default.
- W3022819384 hasConceptScore W3022819384C48659774 @default.
- W3022819384 hasConceptScore W3022819384C80444323 @default.
- W3022819384 hasLocation W30228193841 @default.
- W3022819384 hasOpenAccess W3022819384 @default.
- W3022819384 hasPrimaryLocation W30228193841 @default.
- W3022819384 hasRelatedWork W201567753 @default.
- W3022819384 hasRelatedWork W2020371238 @default.
- W3022819384 hasRelatedWork W2080625687 @default.
- W3022819384 hasRelatedWork W2097754932 @default.
- W3022819384 hasRelatedWork W2291171832 @default.
- W3022819384 hasRelatedWork W2757596774 @default.
- W3022819384 hasRelatedWork W2785125662 @default.
- W3022819384 hasRelatedWork W2797151025 @default.
- W3022819384 hasRelatedWork W2972405501 @default.
- W3022819384 hasRelatedWork W2975249723 @default.
- W3022819384 hasRelatedWork W2981068954 @default.
- W3022819384 hasRelatedWork W2981237571 @default.
- W3022819384 hasRelatedWork W3098520424 @default.
- W3022819384 hasRelatedWork W3101702052 @default.
- W3022819384 hasRelatedWork W3105453593 @default.
- W3022819384 hasRelatedWork W3121922819 @default.
- W3022819384 hasRelatedWork W3147972065 @default.
- W3022819384 hasRelatedWork W70301489 @default.
- W3022819384 hasRelatedWork W74225879 @default.
- W3022819384 hasRelatedWork W2336911432 @default.
- W3022819384 hasVolume "2019" @default.
- W3022819384 isParatext "false" @default.
- W3022819384 isRetracted "false" @default.
- W3022819384 magId "3022819384" @default.
- W3022819384 workType "article" @default.