Matches in SemOpenAlex for { <https://semopenalex.org/work/W3091991462> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W3091991462 endingPage "11415" @default.
- W3091991462 startingPage "11404" @default.
- W3091991462 abstract "Decision Trees (DTs) and Random Forests (RFs) are powerful discriminative learners and tools of central importance to the everyday machine learning practitioner and data scientist. Due to their discriminative nature, however, they lack principled methods to process inputs with missing features or to detect outliers, which requires pairing them with imputation techniques or a separate generative model. In this paper, we demonstrate that DTs and RFs can naturally be interpreted as generative models, by drawing a connection to Probabilistic Circuits, a prominent class of tractable probabilistic models. This reinterpretation equips them with a full joint distribution over the feature space and leads to Generative Decision Trees (GeDTs) and Generative Forests (GeFs), a family of novel hybrid generative-discriminative models. This family of models retains the overall characteristics of DTs and RFs while additionally being able to handle missing features by means of marginalisation. Under certain assumptions, frequently made for Bayes consistency results, we show that consistency in GeDTs and GeFs extend to any pattern of missing input features, if missing at random. Empirically, we show that our models often outperform common routines to treat missing data, such as K-nearest neighbour imputation, and moreover, that our models can naturally detect outliers by monitoring the marginal probability of input features." @default.
- W3091991462 created "2020-10-15" @default.
- W3091991462 creator A5004994425 @default.
- W3091991462 creator A5050783061 @default.
- W3091991462 creator A5057485787 @default.
- W3091991462 date "2020-01-01" @default.
- W3091991462 modified "2023-09-24" @default.
- W3091991462 title "Joints in Random Forests" @default.
- W3091991462 hasPublicationYear "2020" @default.
- W3091991462 type Work @default.
- W3091991462 sameAs 3091991462 @default.
- W3091991462 citedByCount "1" @default.
- W3091991462 countsByYear W30919914622021 @default.
- W3091991462 crossrefType "proceedings-article" @default.
- W3091991462 hasAuthorship W3091991462A5004994425 @default.
- W3091991462 hasAuthorship W3091991462A5050783061 @default.
- W3091991462 hasAuthorship W3091991462A5057485787 @default.
- W3091991462 hasConcept C119857082 @default.
- W3091991462 hasConcept C153180895 @default.
- W3091991462 hasConcept C154945302 @default.
- W3091991462 hasConcept C155846161 @default.
- W3091991462 hasConcept C167966045 @default.
- W3091991462 hasConcept C169258074 @default.
- W3091991462 hasConcept C39890363 @default.
- W3091991462 hasConcept C41008148 @default.
- W3091991462 hasConcept C45942800 @default.
- W3091991462 hasConcept C49937458 @default.
- W3091991462 hasConcept C58041806 @default.
- W3091991462 hasConcept C79337645 @default.
- W3091991462 hasConcept C9357733 @default.
- W3091991462 hasConcept C97931131 @default.
- W3091991462 hasConceptScore W3091991462C119857082 @default.
- W3091991462 hasConceptScore W3091991462C153180895 @default.
- W3091991462 hasConceptScore W3091991462C154945302 @default.
- W3091991462 hasConceptScore W3091991462C155846161 @default.
- W3091991462 hasConceptScore W3091991462C167966045 @default.
- W3091991462 hasConceptScore W3091991462C169258074 @default.
- W3091991462 hasConceptScore W3091991462C39890363 @default.
- W3091991462 hasConceptScore W3091991462C41008148 @default.
- W3091991462 hasConceptScore W3091991462C45942800 @default.
- W3091991462 hasConceptScore W3091991462C49937458 @default.
- W3091991462 hasConceptScore W3091991462C58041806 @default.
- W3091991462 hasConceptScore W3091991462C79337645 @default.
- W3091991462 hasConceptScore W3091991462C9357733 @default.
- W3091991462 hasConceptScore W3091991462C97931131 @default.
- W3091991462 hasLocation W30919914621 @default.
- W3091991462 hasOpenAccess W3091991462 @default.
- W3091991462 hasPrimaryLocation W30919914621 @default.
- W3091991462 hasRelatedWork W2027472744 @default.
- W3091991462 hasRelatedWork W2031782775 @default.
- W3091991462 hasRelatedWork W2103292002 @default.
- W3091991462 hasRelatedWork W2107060372 @default.
- W3091991462 hasRelatedWork W2166473218 @default.
- W3091991462 hasRelatedWork W2275114322 @default.
- W3091991462 hasRelatedWork W2299115575 @default.
- W3091991462 hasRelatedWork W2327469985 @default.
- W3091991462 hasRelatedWork W2618175216 @default.
- W3091991462 hasRelatedWork W2785902771 @default.
- W3091991462 hasRelatedWork W2800482383 @default.
- W3091991462 hasRelatedWork W2944874434 @default.
- W3091991462 hasRelatedWork W2963912395 @default.
- W3091991462 hasRelatedWork W2978864545 @default.
- W3091991462 hasRelatedWork W3013629183 @default.
- W3091991462 hasRelatedWork W3048757909 @default.
- W3091991462 hasRelatedWork W3094678421 @default.
- W3091991462 hasRelatedWork W3116494032 @default.
- W3091991462 hasRelatedWork W3199553118 @default.
- W3091991462 hasRelatedWork W3091947004 @default.
- W3091991462 hasVolume "33" @default.
- W3091991462 isParatext "false" @default.
- W3091991462 isRetracted "false" @default.
- W3091991462 magId "3091991462" @default.
- W3091991462 workType "article" @default.