Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313305603> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4313305603 abstract "Multivariate time series forecasting with hierarchical structure is pervasive in real-world applications, demanding not only predicting each level of the hierarchy, but also reconciling all forecasts to ensure coherency, i.e., the forecasts should satisfy the hierarchical aggregation constraints. Moreover, the disparities of statistical characteristics between levels can be huge, worsened by non-Gaussian distributions and non-linear correlations. To this extent, we propose a novel end-to-end hierarchical time series forecasting model, based on conditioned normalizing flow-based autoregressive transformer reconciliation, to represent complex data distribution while simultaneously reconciling the forecasts to ensure coherency. Unlike other state-of-the-art methods, we achieve the forecasting and reconciliation simultaneously without requiring any explicit post-processing step. In addition, by harnessing the power of deep model, we do not rely on any assumption such as unbiased estimates or Gaussian distribution. Our evaluation experiments are conducted on four real-world hierarchical datasets from different industrial domains (three public ones and a dataset from the application servers of Alipay's data center) and the preliminary results demonstrate efficacy of our proposed method." @default.
- W4313305603 created "2023-01-06" @default.
- W4313305603 creator A5004337233 @default.
- W4313305603 creator A5021671895 @default.
- W4313305603 creator A5026486057 @default.
- W4313305603 creator A5036920814 @default.
- W4313305603 creator A5039360390 @default.
- W4313305603 creator A5044899287 @default.
- W4313305603 creator A5053447705 @default.
- W4313305603 creator A5074034944 @default.
- W4313305603 date "2022-12-28" @default.
- W4313305603 modified "2023-09-26" @default.
- W4313305603 title "End-to-End Modeling Hierarchical Time Series Using Autoregressive Transformer and Conditional Normalizing Flow based Reconciliation" @default.
- W4313305603 doi "https://doi.org/10.48550/arxiv.2212.13706" @default.
- W4313305603 hasPublicationYear "2022" @default.
- W4313305603 type Work @default.
- W4313305603 citedByCount "0" @default.
- W4313305603 crossrefType "posted-content" @default.
- W4313305603 hasAuthorship W4313305603A5004337233 @default.
- W4313305603 hasAuthorship W4313305603A5021671895 @default.
- W4313305603 hasAuthorship W4313305603A5026486057 @default.
- W4313305603 hasAuthorship W4313305603A5036920814 @default.
- W4313305603 hasAuthorship W4313305603A5039360390 @default.
- W4313305603 hasAuthorship W4313305603A5044899287 @default.
- W4313305603 hasAuthorship W4313305603A5053447705 @default.
- W4313305603 hasAuthorship W4313305603A5074034944 @default.
- W4313305603 hasBestOaLocation W43133056031 @default.
- W4313305603 hasConcept C114289077 @default.
- W4313305603 hasConcept C119599485 @default.
- W4313305603 hasConcept C119857082 @default.
- W4313305603 hasConcept C121332964 @default.
- W4313305603 hasConcept C124101348 @default.
- W4313305603 hasConcept C127413603 @default.
- W4313305603 hasConcept C144986985 @default.
- W4313305603 hasConcept C149782125 @default.
- W4313305603 hasConcept C151406439 @default.
- W4313305603 hasConcept C154945302 @default.
- W4313305603 hasConcept C159877910 @default.
- W4313305603 hasConcept C162324750 @default.
- W4313305603 hasConcept C163716315 @default.
- W4313305603 hasConcept C165801399 @default.
- W4313305603 hasConcept C31170391 @default.
- W4313305603 hasConcept C33923547 @default.
- W4313305603 hasConcept C34447519 @default.
- W4313305603 hasConcept C41008148 @default.
- W4313305603 hasConcept C62520636 @default.
- W4313305603 hasConcept C66322947 @default.
- W4313305603 hasConceptScore W4313305603C114289077 @default.
- W4313305603 hasConceptScore W4313305603C119599485 @default.
- W4313305603 hasConceptScore W4313305603C119857082 @default.
- W4313305603 hasConceptScore W4313305603C121332964 @default.
- W4313305603 hasConceptScore W4313305603C124101348 @default.
- W4313305603 hasConceptScore W4313305603C127413603 @default.
- W4313305603 hasConceptScore W4313305603C144986985 @default.
- W4313305603 hasConceptScore W4313305603C149782125 @default.
- W4313305603 hasConceptScore W4313305603C151406439 @default.
- W4313305603 hasConceptScore W4313305603C154945302 @default.
- W4313305603 hasConceptScore W4313305603C159877910 @default.
- W4313305603 hasConceptScore W4313305603C162324750 @default.
- W4313305603 hasConceptScore W4313305603C163716315 @default.
- W4313305603 hasConceptScore W4313305603C165801399 @default.
- W4313305603 hasConceptScore W4313305603C31170391 @default.
- W4313305603 hasConceptScore W4313305603C33923547 @default.
- W4313305603 hasConceptScore W4313305603C34447519 @default.
- W4313305603 hasConceptScore W4313305603C41008148 @default.
- W4313305603 hasConceptScore W4313305603C62520636 @default.
- W4313305603 hasConceptScore W4313305603C66322947 @default.
- W4313305603 hasLocation W43133056031 @default.
- W4313305603 hasOpenAccess W4313305603 @default.
- W4313305603 hasPrimaryLocation W43133056031 @default.
- W4313305603 hasRelatedWork W10368213 @default.
- W4313305603 hasRelatedWork W2050718917 @default.
- W4313305603 hasRelatedWork W2139220179 @default.
- W4313305603 hasRelatedWork W2176721405 @default.
- W4313305603 hasRelatedWork W2238429300 @default.
- W4313305603 hasRelatedWork W2360459119 @default.
- W4313305603 hasRelatedWork W3112967555 @default.
- W4313305603 hasRelatedWork W3128155778 @default.
- W4313305603 hasRelatedWork W4243783011 @default.
- W4313305603 hasRelatedWork W635556284 @default.
- W4313305603 isParatext "false" @default.
- W4313305603 isRetracted "false" @default.
- W4313305603 workType "article" @default.