Matches in SemOpenAlex for { <https://semopenalex.org/work/W3144098990> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3144098990 abstract "The predictive advantage of combining several different predictive models is widely accepted. Particularly in time series forecasting problems, this combination is often dynamic to cope with potential non-stationary sources of variation present in the data. Despite their superior predictive performance, ensemble methods entail two main limitations: high computational costs and lack of transparency. These issues often preclude the deployment of such approaches, in favour of simpler yet more efficient and reliable ones. In this paper, we leverage the idea of model compression to address this problem in time series forecasting tasks. Model compression approaches have been mostly unexplored for forecasting. Their application in time series is challenging due to the evolving nature of the data. Further, while the literature focuses on neural networks, we apply model compression to distinct types of methods. In an extensive set of experiments, we show that compressing dynamic forecasting ensembles into an individual model leads to a comparable predictive performance and a drastic reduction in computational costs. Further, the compressed individual model with best average rank is a rule-based regression model. Thus, model compression also leads to benefits in terms of model interpretability. The experiments carried in this paper are fully reproducible." @default.
- W3144098990 created "2021-04-13" @default.
- W3144098990 creator A5018859851 @default.
- W3144098990 creator A5058183984 @default.
- W3144098990 creator A5080727549 @default.
- W3144098990 creator A5080970505 @default.
- W3144098990 date "2021-04-05" @default.
- W3144098990 modified "2023-09-27" @default.
- W3144098990 title "Model Compression for Dynamic Forecast Combination" @default.
- W3144098990 cites W13338109 @default.
- W3144098990 cites W1481566577 @default.
- W3144098990 cites W1570963478 @default.
- W3144098990 cites W1693343509 @default.
- W3144098990 cites W1980264541 @default.
- W3144098990 cites W1986528915 @default.
- W3144098990 cites W1996063690 @default.
- W3144098990 cites W2001507422 @default.
- W3144098990 cites W2016210396 @default.
- W3144098990 cites W2057182962 @default.
- W3144098990 cites W2100483895 @default.
- W3144098990 cites W2102201073 @default.
- W3144098990 cites W2124951716 @default.
- W3144098990 cites W2148825261 @default.
- W3144098990 cites W2157963336 @default.
- W3144098990 cites W2245178135 @default.
- W3144098990 cites W2367397349 @default.
- W3144098990 cites W2543539599 @default.
- W3144098990 cites W2582743722 @default.
- W3144098990 cites W2620998106 @default.
- W3144098990 cites W27682692 @default.
- W3144098990 cites W2783209257 @default.
- W3144098990 cites W2794778778 @default.
- W3144098990 cites W2811189031 @default.
- W3144098990 cites W2901999103 @default.
- W3144098990 cites W2909973217 @default.
- W3144098990 cites W2962772482 @default.
- W3144098990 cites W2963313239 @default.
- W3144098990 cites W2964118293 @default.
- W3144098990 cites W2964306570 @default.
- W3144098990 cites W2975962152 @default.
- W3144098990 hasPublicationYear "2021" @default.
- W3144098990 type Work @default.
- W3144098990 sameAs 3144098990 @default.
- W3144098990 citedByCount "0" @default.
- W3144098990 crossrefType "posted-content" @default.
- W3144098990 hasAuthorship W3144098990A5018859851 @default.
- W3144098990 hasAuthorship W3144098990A5058183984 @default.
- W3144098990 hasAuthorship W3144098990A5080727549 @default.
- W3144098990 hasAuthorship W3144098990A5080970505 @default.
- W3144098990 hasConcept C119857082 @default.
- W3144098990 hasConcept C124101348 @default.
- W3144098990 hasConcept C151406439 @default.
- W3144098990 hasConcept C153083717 @default.
- W3144098990 hasConcept C154945302 @default.
- W3144098990 hasConcept C2781067378 @default.
- W3144098990 hasConcept C41008148 @default.
- W3144098990 hasConcept C45804977 @default.
- W3144098990 hasConcept C50644808 @default.
- W3144098990 hasConcept C78548338 @default.
- W3144098990 hasConceptScore W3144098990C119857082 @default.
- W3144098990 hasConceptScore W3144098990C124101348 @default.
- W3144098990 hasConceptScore W3144098990C151406439 @default.
- W3144098990 hasConceptScore W3144098990C153083717 @default.
- W3144098990 hasConceptScore W3144098990C154945302 @default.
- W3144098990 hasConceptScore W3144098990C2781067378 @default.
- W3144098990 hasConceptScore W3144098990C41008148 @default.
- W3144098990 hasConceptScore W3144098990C45804977 @default.
- W3144098990 hasConceptScore W3144098990C50644808 @default.
- W3144098990 hasConceptScore W3144098990C78548338 @default.
- W3144098990 hasLocation W31440989901 @default.
- W3144098990 hasOpenAccess W3144098990 @default.
- W3144098990 hasPrimaryLocation W31440989901 @default.
- W3144098990 hasRelatedWork W1586662829 @default.
- W3144098990 hasRelatedWork W1720020285 @default.
- W3144098990 hasRelatedWork W198604986 @default.
- W3144098990 hasRelatedWork W2037774479 @default.
- W3144098990 hasRelatedWork W2547949325 @default.
- W3144098990 hasRelatedWork W2570854297 @default.
- W3144098990 hasRelatedWork W2783209257 @default.
- W3144098990 hasRelatedWork W2806974224 @default.
- W3144098990 hasRelatedWork W2904258705 @default.
- W3144098990 hasRelatedWork W2937736646 @default.
- W3144098990 hasRelatedWork W2942942449 @default.
- W3144098990 hasRelatedWork W2950846878 @default.
- W3144098990 hasRelatedWork W2953243473 @default.
- W3144098990 hasRelatedWork W3106667652 @default.
- W3144098990 hasRelatedWork W3120862840 @default.
- W3144098990 hasRelatedWork W3161181652 @default.
- W3144098990 hasRelatedWork W3172514114 @default.
- W3144098990 hasRelatedWork W3190712539 @default.
- W3144098990 hasRelatedWork W3207461855 @default.
- W3144098990 hasRelatedWork W2991889589 @default.
- W3144098990 isParatext "false" @default.
- W3144098990 isRetracted "false" @default.
- W3144098990 magId "3144098990" @default.
- W3144098990 workType "article" @default.