Matches in SemOpenAlex for { <https://semopenalex.org/work/W2101924054> ?p ?o ?g. }
- W2101924054 abstract "Many real-world regression problems demand a measure of the uncertainty associated with each prediction. Standard decision forests deliver efficient state-of-the-art predictive performance, but high-quality uncertainty estimates are lacking. Gaussian processes (GPs) deliver uncertainty estimates, but scaling GPs to large-scale data sets comes at the cost of approximating the uncertainty estimates. We extend Mondrian forests, first proposed by Lakshminarayanan et al. (2014) for classification problems, to the large-scale non-parametric regression setting. Using a novel hierarchical Gaussian prior that dovetails with the Mondrian forest framework, we obtain principled uncertainty estimates, while still retaining the computational advantages of decision forests. Through a combination of illustrative examples, real-world large-scale datasets, and Bayesian optimization benchmarks, we demonstrate that Mondrian forests outperform approximate GPs on large-scale regression tasks and deliver better-calibrated uncertainty assessments than decision-forest-based methods." @default.
- W2101924054 created "2016-06-24" @default.
- W2101924054 creator A5012859570 @default.
- W2101924054 creator A5042384857 @default.
- W2101924054 creator A5064373793 @default.
- W2101924054 date "2015-06-11" @default.
- W2101924054 modified "2023-09-26" @default.
- W2101924054 title "Mondrian Forests for Large-Scale Regression when Uncertainty Matters" @default.
- W2101924054 cites W137285897 @default.
- W2101924054 cites W1503398984 @default.
- W2101924054 cites W1579064899 @default.
- W2101924054 cites W1780422458 @default.
- W2101924054 cites W2056132907 @default.
- W2101924054 cites W2058224795 @default.
- W2101924054 cites W2099201756 @default.
- W2101924054 cites W2129018774 @default.
- W2101924054 cites W2144207912 @default.
- W2101924054 cites W2158471180 @default.
- W2101924054 cites W2159080219 @default.
- W2101924054 cites W2159187228 @default.
- W2101924054 cites W2911964244 @default.
- W2101924054 cites W2949536823 @default.
- W2101924054 cites W2949971467 @default.
- W2101924054 cites W2950182411 @default.
- W2101924054 cites W2950277768 @default.
- W2101924054 cites W2951665052 @default.
- W2101924054 cites W2952677397 @default.
- W2101924054 cites W2964281761 @default.
- W2101924054 cites W3124229194 @default.
- W2101924054 hasPublicationYear "2015" @default.
- W2101924054 type Work @default.
- W2101924054 sameAs 2101924054 @default.
- W2101924054 citedByCount "1" @default.
- W2101924054 countsByYear W21019240542015 @default.
- W2101924054 crossrefType "posted-content" @default.
- W2101924054 hasAuthorship W2101924054A5012859570 @default.
- W2101924054 hasAuthorship W2101924054A5042384857 @default.
- W2101924054 hasAuthorship W2101924054A5064373793 @default.
- W2101924054 hasConcept C105795698 @default.
- W2101924054 hasConcept C107673813 @default.
- W2101924054 hasConcept C117251300 @default.
- W2101924054 hasConcept C119857082 @default.
- W2101924054 hasConcept C124101348 @default.
- W2101924054 hasConcept C142362112 @default.
- W2101924054 hasConcept C149782125 @default.
- W2101924054 hasConcept C153349607 @default.
- W2101924054 hasConcept C154945302 @default.
- W2101924054 hasConcept C169258074 @default.
- W2101924054 hasConcept C205649164 @default.
- W2101924054 hasConcept C205783811 @default.
- W2101924054 hasConcept C2778755073 @default.
- W2101924054 hasConcept C2779075496 @default.
- W2101924054 hasConcept C33923547 @default.
- W2101924054 hasConcept C41008148 @default.
- W2101924054 hasConcept C58640448 @default.
- W2101924054 hasConcept C60229501 @default.
- W2101924054 hasConcept C76155785 @default.
- W2101924054 hasConcept C83546350 @default.
- W2101924054 hasConcept C84525736 @default.
- W2101924054 hasConceptScore W2101924054C105795698 @default.
- W2101924054 hasConceptScore W2101924054C107673813 @default.
- W2101924054 hasConceptScore W2101924054C117251300 @default.
- W2101924054 hasConceptScore W2101924054C119857082 @default.
- W2101924054 hasConceptScore W2101924054C124101348 @default.
- W2101924054 hasConceptScore W2101924054C142362112 @default.
- W2101924054 hasConceptScore W2101924054C149782125 @default.
- W2101924054 hasConceptScore W2101924054C153349607 @default.
- W2101924054 hasConceptScore W2101924054C154945302 @default.
- W2101924054 hasConceptScore W2101924054C169258074 @default.
- W2101924054 hasConceptScore W2101924054C205649164 @default.
- W2101924054 hasConceptScore W2101924054C205783811 @default.
- W2101924054 hasConceptScore W2101924054C2778755073 @default.
- W2101924054 hasConceptScore W2101924054C2779075496 @default.
- W2101924054 hasConceptScore W2101924054C33923547 @default.
- W2101924054 hasConceptScore W2101924054C41008148 @default.
- W2101924054 hasConceptScore W2101924054C58640448 @default.
- W2101924054 hasConceptScore W2101924054C60229501 @default.
- W2101924054 hasConceptScore W2101924054C76155785 @default.
- W2101924054 hasConceptScore W2101924054C83546350 @default.
- W2101924054 hasConceptScore W2101924054C84525736 @default.
- W2101924054 hasLocation W21019240541 @default.
- W2101924054 hasOpenAccess W2101924054 @default.
- W2101924054 hasPrimaryLocation W21019240541 @default.
- W2101924054 hasRelatedWork W2560321925 @default.
- W2101924054 hasRelatedWork W2804073540 @default.
- W2101924054 hasRelatedWork W2947216528 @default.
- W2101924054 hasRelatedWork W2950317294 @default.
- W2101924054 hasRelatedWork W2963081736 @default.
- W2101924054 hasRelatedWork W2963215553 @default.
- W2101924054 hasRelatedWork W2963754144 @default.
- W2101924054 hasRelatedWork W2989383883 @default.
- W2101924054 hasRelatedWork W2996246027 @default.
- W2101924054 hasRelatedWork W3005789139 @default.
- W2101924054 hasRelatedWork W3039386209 @default.
- W2101924054 hasRelatedWork W3039909089 @default.
- W2101924054 hasRelatedWork W3126303737 @default.
- W2101924054 hasRelatedWork W3128958304 @default.
- W2101924054 hasRelatedWork W3129661423 @default.
- W2101924054 hasRelatedWork W3132565318 @default.
- W2101924054 hasRelatedWork W3163155043 @default.