Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213199902> ?p ?o ?g. }
- W3213199902 abstract "While classical time series forecasting considers individual time series in isolation, recent advances based on deep learning showed that jointly learning from a large pool of related time series can boost the forecasting accuracy. However, the accuracy of these methods suffers greatly when modeling out-of-sample time series, significantly limiting their applicability compared to classical forecasting methods. To bridge this gap, we adopt a meta-learning view of the time series forecasting problem. We introduce a novel forecasting method, called Meta Global-Local Auto-Regression (Meta-GLAR), that adapts to each time series by learning in closed-form the mapping from the representations produced by a recurrent neural network (RNN) to one-step-ahead forecasts. Crucially, the parameters ofthe RNN are learned across multiple time series by backpropagating through the closed-form adaptation mechanism. In our extensive empirical evaluation we show that our method is competitive with the state-of-the-art in out-of-sample forecasting accuracy reported in earlier work." @default.
- W3213199902 created "2021-11-22" @default.
- W3213199902 creator A5005126104 @default.
- W3213199902 creator A5005681375 @default.
- W3213199902 creator A5021107714 @default.
- W3213199902 creator A5026334888 @default.
- W3213199902 creator A5034665821 @default.
- W3213199902 creator A5078696011 @default.
- W3213199902 date "2021-11-05" @default.
- W3213199902 modified "2023-09-27" @default.
- W3213199902 title "Meta-Forecasting by combining Global Deep Representations with Local Adaptation." @default.
- W3213199902 cites W1522301498 @default.
- W3213199902 cites W1977698057 @default.
- W3213199902 cites W1981487036 @default.
- W3213199902 cites W2016210396 @default.
- W3213199902 cites W2048665112 @default.
- W3213199902 cites W2064675550 @default.
- W3213199902 cites W2079560958 @default.
- W3213199902 cites W2146525523 @default.
- W3213199902 cites W2194775991 @default.
- W3213199902 cites W2409027918 @default.
- W3213199902 cites W2549483845 @default.
- W3213199902 cites W2604763608 @default.
- W3213199902 cites W2753160622 @default.
- W3213199902 cites W2788408785 @default.
- W3213199902 cites W2794363191 @default.
- W3213199902 cites W2795900505 @default.
- W3213199902 cites W2811507150 @default.
- W3213199902 cites W2883806129 @default.
- W3213199902 cites W2909973217 @default.
- W3213199902 cites W2920777619 @default.
- W3213199902 cites W2948858042 @default.
- W3213199902 cites W2950304420 @default.
- W3213199902 cites W2950537964 @default.
- W3213199902 cites W2950846878 @default.
- W3213199902 cites W2954090070 @default.
- W3213199902 cites W2962752580 @default.
- W3213199902 cites W2963341924 @default.
- W3213199902 cites W2963507686 @default.
- W3213199902 cites W2964105864 @default.
- W3213199902 cites W2964206659 @default.
- W3213199902 cites W2970309699 @default.
- W3213199902 cites W2970631142 @default.
- W3213199902 cites W2970791107 @default.
- W3213199902 cites W2980994438 @default.
- W3213199902 cites W2995049146 @default.
- W3213199902 cites W2996331899 @default.
- W3213199902 cites W2996552856 @default.
- W3213199902 cites W3013644914 @default.
- W3213199902 cites W3042623101 @default.
- W3213199902 cites W3083007398 @default.
- W3213199902 cites W3090339165 @default.
- W3213199902 cites W3096277532 @default.
- W3213199902 cites W3111605943 @default.
- W3213199902 cites W3120740533 @default.
- W3213199902 cites W3123547113 @default.
- W3213199902 cites W3129365350 @default.
- W3213199902 cites W3005326476 @default.
- W3213199902 hasPublicationYear "2021" @default.
- W3213199902 type Work @default.
- W3213199902 sameAs 3213199902 @default.
- W3213199902 citedByCount "0" @default.
- W3213199902 crossrefType "posted-content" @default.
- W3213199902 hasAuthorship W3213199902A5005126104 @default.
- W3213199902 hasAuthorship W3213199902A5005681375 @default.
- W3213199902 hasAuthorship W3213199902A5021107714 @default.
- W3213199902 hasAuthorship W3213199902A5026334888 @default.
- W3213199902 hasAuthorship W3213199902A5034665821 @default.
- W3213199902 hasAuthorship W3213199902A5078696011 @default.
- W3213199902 hasConcept C105795698 @default.
- W3213199902 hasConcept C108583219 @default.
- W3213199902 hasConcept C119857082 @default.
- W3213199902 hasConcept C122282355 @default.
- W3213199902 hasConcept C143724316 @default.
- W3213199902 hasConcept C147168706 @default.
- W3213199902 hasConcept C151406439 @default.
- W3213199902 hasConcept C151730666 @default.
- W3213199902 hasConcept C154945302 @default.
- W3213199902 hasConcept C162324750 @default.
- W3213199902 hasConcept C185592680 @default.
- W3213199902 hasConcept C187736073 @default.
- W3213199902 hasConcept C198531522 @default.
- W3213199902 hasConcept C2780451532 @default.
- W3213199902 hasConcept C2781002164 @default.
- W3213199902 hasConcept C33923547 @default.
- W3213199902 hasConcept C41008148 @default.
- W3213199902 hasConcept C43617362 @default.
- W3213199902 hasConcept C49937458 @default.
- W3213199902 hasConcept C50644808 @default.
- W3213199902 hasConcept C83546350 @default.
- W3213199902 hasConcept C86803240 @default.
- W3213199902 hasConceptScore W3213199902C105795698 @default.
- W3213199902 hasConceptScore W3213199902C108583219 @default.
- W3213199902 hasConceptScore W3213199902C119857082 @default.
- W3213199902 hasConceptScore W3213199902C122282355 @default.
- W3213199902 hasConceptScore W3213199902C143724316 @default.
- W3213199902 hasConceptScore W3213199902C147168706 @default.
- W3213199902 hasConceptScore W3213199902C151406439 @default.
- W3213199902 hasConceptScore W3213199902C151730666 @default.
- W3213199902 hasConceptScore W3213199902C154945302 @default.