Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890032783> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2890032783 abstract "We propose a modified spectral mixture (SM) kernel that serves as a universal stationary kernel for temporal Gaussian process regression (GPR). The kernel is named grid spectral mixture (GSM) kernel as we fix the frequency and variance parameters in the original SM kernel to a set of pre-selected grid points. The hyper-parameters are the non-negative weights of all sub-kernel functions and the resulting optimization task falls under the difference-of-convex programming. Due to the nice structure of the optimization problem, the hyper-parameters are solved by an efficient majorization-minimization method instead of the gradient descent methods. It turns out that the solution is sparse, which provides us with a principled guideline to identify the important frequency components of the data. Experimental results based on various classic time series data sets corroborate that the proposed GPR with GSM kernel significantly outperforms the GPR with SM kernel in terms of both the mean-squared-error (MSE) and the stability of the optimization algorithm." @default.
- W2890032783 created "2018-09-27" @default.
- W2890032783 creator A5036492388 @default.
- W2890032783 creator A5047025816 @default.
- W2890032783 creator A5050056521 @default.
- W2890032783 creator A5085953846 @default.
- W2890032783 creator A5087473873 @default.
- W2890032783 creator A5091724499 @default.
- W2890032783 date "2018-07-01" @default.
- W2890032783 modified "2023-09-29" @default.
- W2890032783 title "Sparse Structure Enabled Grid Spectral Mixture Kernel for Temporal Gaussian Process Regression" @default.
- W2890032783 cites W1973310094 @default.
- W2890032783 cites W1999479532 @default.
- W2890032783 cites W2086901931 @default.
- W2890032783 cites W2097795807 @default.
- W2890032783 cites W2117756735 @default.
- W2890032783 cites W2148154358 @default.
- W2890032783 cites W2564963669 @default.
- W2890032783 cites W2783656730 @default.
- W2890032783 cites W2963754333 @default.
- W2890032783 cites W2963774371 @default.
- W2890032783 doi "https://doi.org/10.23919/icif.2018.8455284" @default.
- W2890032783 hasPublicationYear "2018" @default.
- W2890032783 type Work @default.
- W2890032783 sameAs 2890032783 @default.
- W2890032783 citedByCount "8" @default.
- W2890032783 countsByYear W28900327832018 @default.
- W2890032783 countsByYear W28900327832019 @default.
- W2890032783 countsByYear W28900327832020 @default.
- W2890032783 countsByYear W28900327832021 @default.
- W2890032783 crossrefType "proceedings-article" @default.
- W2890032783 hasAuthorship W2890032783A5036492388 @default.
- W2890032783 hasAuthorship W2890032783A5047025816 @default.
- W2890032783 hasAuthorship W2890032783A5050056521 @default.
- W2890032783 hasAuthorship W2890032783A5085953846 @default.
- W2890032783 hasAuthorship W2890032783A5087473873 @default.
- W2890032783 hasAuthorship W2890032783A5091724499 @default.
- W2890032783 hasConcept C105795698 @default.
- W2890032783 hasConcept C111919701 @default.
- W2890032783 hasConcept C114614502 @default.
- W2890032783 hasConcept C119857082 @default.
- W2890032783 hasConcept C121332964 @default.
- W2890032783 hasConcept C153180895 @default.
- W2890032783 hasConcept C154945302 @default.
- W2890032783 hasConcept C163716315 @default.
- W2890032783 hasConcept C187691185 @default.
- W2890032783 hasConcept C200695384 @default.
- W2890032783 hasConcept C2524010 @default.
- W2890032783 hasConcept C33923547 @default.
- W2890032783 hasConcept C41008148 @default.
- W2890032783 hasConcept C61326573 @default.
- W2890032783 hasConcept C62520636 @default.
- W2890032783 hasConcept C74193536 @default.
- W2890032783 hasConcept C81692654 @default.
- W2890032783 hasConcept C83546350 @default.
- W2890032783 hasConcept C98045186 @default.
- W2890032783 hasConceptScore W2890032783C105795698 @default.
- W2890032783 hasConceptScore W2890032783C111919701 @default.
- W2890032783 hasConceptScore W2890032783C114614502 @default.
- W2890032783 hasConceptScore W2890032783C119857082 @default.
- W2890032783 hasConceptScore W2890032783C121332964 @default.
- W2890032783 hasConceptScore W2890032783C153180895 @default.
- W2890032783 hasConceptScore W2890032783C154945302 @default.
- W2890032783 hasConceptScore W2890032783C163716315 @default.
- W2890032783 hasConceptScore W2890032783C187691185 @default.
- W2890032783 hasConceptScore W2890032783C200695384 @default.
- W2890032783 hasConceptScore W2890032783C2524010 @default.
- W2890032783 hasConceptScore W2890032783C33923547 @default.
- W2890032783 hasConceptScore W2890032783C41008148 @default.
- W2890032783 hasConceptScore W2890032783C61326573 @default.
- W2890032783 hasConceptScore W2890032783C62520636 @default.
- W2890032783 hasConceptScore W2890032783C74193536 @default.
- W2890032783 hasConceptScore W2890032783C81692654 @default.
- W2890032783 hasConceptScore W2890032783C83546350 @default.
- W2890032783 hasConceptScore W2890032783C98045186 @default.
- W2890032783 hasLocation W28900327831 @default.
- W2890032783 hasOpenAccess W2890032783 @default.
- W2890032783 hasPrimaryLocation W28900327831 @default.
- W2890032783 hasRelatedWork W2304443721 @default.
- W2890032783 hasRelatedWork W2376872241 @default.
- W2890032783 hasRelatedWork W2492335913 @default.
- W2890032783 hasRelatedWork W2574959498 @default.
- W2890032783 hasRelatedWork W3185162181 @default.
- W2890032783 hasRelatedWork W3211158205 @default.
- W2890032783 hasRelatedWork W3214344677 @default.
- W2890032783 hasRelatedWork W3215147392 @default.
- W2890032783 hasRelatedWork W3217770377 @default.
- W2890032783 hasRelatedWork W4287073795 @default.
- W2890032783 isParatext "false" @default.
- W2890032783 isRetracted "false" @default.
- W2890032783 magId "2890032783" @default.
- W2890032783 workType "article" @default.