Matches in SemOpenAlex for { <https://semopenalex.org/work/W3161082783> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3161082783 abstract "Learning a suitable graph is an important precursor to many graph signal processing (GSP) pipelines, such as graph signal compression and denoising. Previous graph learning algorithms either i) make assumptions on graph connectivity (e.g., graph sparsity), or ii) make edge weight assumptions such as positive edges only. In this paper, given an empirical covariance matrix ${mathbf{bar C}}$ computed from data as input, we consider an eigen-structural assumption on the graph Laplacian matrix L: the first K eigenvectors of L are pre-selected, e.g., based on domain-specific criteria, and the remaining eigenvectors are then learned from data. One example use case is image coding, where the first eigenvector is pre-chosen to be constant, regardless of available observed data. We first prove that the subspace $mathcal{H}_{mathbf{u}}^ + $ of symmetric positive semi-definite (PSD) matrices with the first K eigenvectors being {u <inf xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>k</inf> } in a defined Hilbert space is a convex cone. We then construct an operator to project a given positive definite (PD) matrix L to $mathcal{H}_{mathbf{u}}^ + $, inspired by the Gram-Schmidt procedure. Finally, we design an efficient hybrid graphical lasso / projection algorithm to compute the most suitable graph Laplacian matrix ${{mathbf{L}}^ * } in mathcal{H}_{mathbf{u}}^ + $ given ${mathbf{bar C}}$. Experimental results show that given the first K eigenvectors as a prior, our algorithm outperforms competing graph learning schemes using a variety of graph comparison metrics." @default.
- W3161082783 created "2021-05-24" @default.
- W3161082783 creator A5038897476 @default.
- W3161082783 creator A5040001106 @default.
- W3161082783 creator A5063893941 @default.
- W3161082783 creator A5065797163 @default.
- W3161082783 date "2021-06-06" @default.
- W3161082783 modified "2023-09-23" @default.
- W3161082783 title "Learning Sparse Graph Laplacian with K Eigenvector Prior via Iterative Glasso and Projection" @default.
- W3161082783 cites W1980811840 @default.
- W3161082783 cites W1989727964 @default.
- W3161082783 cites W2000769684 @default.
- W3161082783 cites W2051142108 @default.
- W3161082783 cites W2082119873 @default.
- W3161082783 cites W2105760337 @default.
- W3161082783 cites W2126841255 @default.
- W3161082783 cites W2132555912 @default.
- W3161082783 cites W2615556757 @default.
- W3161082783 cites W2796431263 @default.
- W3161082783 cites W2963557697 @default.
- W3161082783 cites W2964012239 @default.
- W3161082783 cites W2964292630 @default.
- W3161082783 cites W2991388718 @default.
- W3161082783 cites W3003775208 @default.
- W3161082783 cites W3018660603 @default.
- W3161082783 cites W3106135392 @default.
- W3161082783 cites W4214926737 @default.
- W3161082783 cites W4230938240 @default.
- W3161082783 cites W4244393449 @default.
- W3161082783 cites W4250589301 @default.
- W3161082783 cites W658512522 @default.
- W3161082783 doi "https://doi.org/10.1109/icassp39728.2021.9414693" @default.
- W3161082783 hasPublicationYear "2021" @default.
- W3161082783 type Work @default.
- W3161082783 sameAs 3161082783 @default.
- W3161082783 citedByCount "2" @default.
- W3161082783 countsByYear W31610827832022 @default.
- W3161082783 countsByYear W31610827832023 @default.
- W3161082783 crossrefType "proceedings-article" @default.
- W3161082783 hasAuthorship W3161082783A5038897476 @default.
- W3161082783 hasAuthorship W3161082783A5040001106 @default.
- W3161082783 hasAuthorship W3161082783A5063893941 @default.
- W3161082783 hasAuthorship W3161082783A5065797163 @default.
- W3161082783 hasBestOaLocation W31610827832 @default.
- W3161082783 hasConcept C11413529 @default.
- W3161082783 hasConcept C114614502 @default.
- W3161082783 hasConcept C115178988 @default.
- W3161082783 hasConcept C118615104 @default.
- W3161082783 hasConcept C121332964 @default.
- W3161082783 hasConcept C132525143 @default.
- W3161082783 hasConcept C134306372 @default.
- W3161082783 hasConcept C158693339 @default.
- W3161082783 hasConcept C165700671 @default.
- W3161082783 hasConcept C180356752 @default.
- W3161082783 hasConcept C33923547 @default.
- W3161082783 hasConcept C49712288 @default.
- W3161082783 hasConcept C62520636 @default.
- W3161082783 hasConcept C7948225 @default.
- W3161082783 hasConceptScore W3161082783C11413529 @default.
- W3161082783 hasConceptScore W3161082783C114614502 @default.
- W3161082783 hasConceptScore W3161082783C115178988 @default.
- W3161082783 hasConceptScore W3161082783C118615104 @default.
- W3161082783 hasConceptScore W3161082783C121332964 @default.
- W3161082783 hasConceptScore W3161082783C132525143 @default.
- W3161082783 hasConceptScore W3161082783C134306372 @default.
- W3161082783 hasConceptScore W3161082783C158693339 @default.
- W3161082783 hasConceptScore W3161082783C165700671 @default.
- W3161082783 hasConceptScore W3161082783C180356752 @default.
- W3161082783 hasConceptScore W3161082783C33923547 @default.
- W3161082783 hasConceptScore W3161082783C49712288 @default.
- W3161082783 hasConceptScore W3161082783C62520636 @default.
- W3161082783 hasConceptScore W3161082783C7948225 @default.
- W3161082783 hasLocation W31610827831 @default.
- W3161082783 hasLocation W31610827832 @default.
- W3161082783 hasLocation W31610827833 @default.
- W3161082783 hasOpenAccess W3161082783 @default.
- W3161082783 hasPrimaryLocation W31610827831 @default.
- W3161082783 hasRelatedWork W18687971 @default.
- W3161082783 hasRelatedWork W1996010389 @default.
- W3161082783 hasRelatedWork W2030274157 @default.
- W3161082783 hasRelatedWork W2031498676 @default.
- W3161082783 hasRelatedWork W2056449679 @default.
- W3161082783 hasRelatedWork W2298820818 @default.
- W3161082783 hasRelatedWork W2384465505 @default.
- W3161082783 hasRelatedWork W2584335808 @default.
- W3161082783 hasRelatedWork W3132233781 @default.
- W3161082783 hasRelatedWork W4318719563 @default.
- W3161082783 isParatext "false" @default.
- W3161082783 isRetracted "false" @default.
- W3161082783 magId "3161082783" @default.
- W3161082783 workType "article" @default.