FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989402453> ?p ?o ?g. }

• W2989402453 endingPage "966" @default.
• W2989402453 startingPage "944" @default.
• W2989402453 abstract "This paper studies a tensor-structured linear regression model with a scalar response variable and tensor-structured predictors, such that the regression parameters form a tensor of order $d$ (i.e., a $d$-fold multiway array) in $mathbb{R}^{n_1 times n_2 times cdots times n_d}$. It focuses on the task of estimating the regression tensor from $m$ realizations of the response variable and the predictors where $mll n = prod nolimits_{i} n_i$. Despite the seeming ill-posedness of this problem, it can still be solved if the parameter tensor belongs to the space of sparse, low Tucker-rank tensors. Accordingly, the estimation procedure is posed as a non-convex optimization program over the space of sparse, low Tucker-rank tensors, and a tensor variant of projected gradient descent is proposed to solve the resulting non-convex problem. In addition, mathematical guarantees are provided that establish the proposed method linearly converges to an appropriate solution under a certain set of conditions. Further, an upper bound on sample complexity of tensor parameter estimation for the model under consideration is characterized for the special case when the individual (scalar) predictors independently draw values from a sub-Gaussian distribution. The sample complexity bound is shown to have a polylogarithmic dependence on $bar{n} = max big{n_i: iin {1,2,ldots,d } big}$ and, orderwise, it matches the bound one can obtain from a heuristic parameter counting argument. Finally, numerical experiments demonstrate the efficacy of the proposed tensor model and estimation method on a synthetic dataset and a collection of neuroimaging datasets pertaining to attention deficit hyperactivity disorder. Specifically, the proposed method exhibits better sample complexities on both synthetic and real datasets, demonstrating the usefulness of the model and the method in settings where $n gg m$." @default.
• W2989402453 created "2019-11-22" @default.
• W2989402453 creator A5014098711 @default.
• W2989402453 creator A5028718006 @default.
• W2989402453 creator A5058429805 @default.
• W2989402453 date "2020-01-01" @default.
• W2989402453 modified "2023-10-14" @default.
• W2989402453 title "Tensor Regression Using Low-Rank and Sparse Tucker Decompositions" @default.
• W2989402453 cites W1967077133 @default.
• W2989402453 cites W1975900269 @default.
• W2989402453 cites W2015418199 @default.
• W2989402453 cites W2020925091 @default.
• W2989402453 cites W2024165284 @default.
• W2989402453 cites W2024254345 @default.
• W2989402453 cites W2045185094 @default.
• W2989402453 cites W2061370212 @default.
• W2989402453 cites W2069231830 @default.
• W2989402453 cites W2078677240 @default.
• W2989402453 cites W2088272457 @default.
• W2989402453 cites W2091449379 @default.
• W2989402453 cites W2100634972 @default.
• W2989402453 cites W2101282194 @default.
• W2989402453 cites W2105026179 @default.
• W2989402453 cites W2117790027 @default.
• W2989402453 cites W2122825543 @default.
• W2989402453 cites W2136002544 @default.
• W2989402453 cites W2143205523 @default.
• W2989402453 cites W2162451874 @default.
• W2989402453 cites W2163886442 @default.
• W2989402453 cites W2469230926 @default.
• W2989402453 cites W2950568021 @default.
• W2989402453 cites W2963116674 @default.
• W2989402453 cites W2963322354 @default.
• W2989402453 cites W2963924474 @default.
• W2989402453 cites W301343586 @default.
• W2989402453 cites W3105340263 @default.
• W2989402453 cites W4205184193 @default.
• W2989402453 doi "https://doi.org/10.1137/19m1299335" @default.
• W2989402453 hasPublicationYear "2020" @default.
• W2989402453 type Work @default.
• W2989402453 sameAs 2989402453 @default.
• W2989402453 citedByCount "8" @default.
• W2989402453 countsByYear W29894024532021 @default.
• W2989402453 countsByYear W29894024532022 @default.
• W2989402453 countsByYear W29894024532023 @default.
• W2989402453 crossrefType "journal-article" @default.
• W2989402453 hasAuthorship W2989402453A5014098711 @default.
• W2989402453 hasAuthorship W2989402453A5028718006 @default.
• W2989402453 hasAuthorship W2989402453A5058429805 @default.
• W2989402453 hasBestOaLocation W29894024531 @default.
• W2989402453 hasConcept C105795698 @default.
• W2989402453 hasConcept C114614502 @default.
• W2989402453 hasConcept C121332964 @default.
• W2989402453 hasConcept C134306372 @default.
• W2989402453 hasConcept C155281189 @default.
• W2989402453 hasConcept C163716315 @default.
• W2989402453 hasConcept C164226766 @default.
• W2989402453 hasConcept C20178491 @default.
• W2989402453 hasConcept C202444582 @default.
• W2989402453 hasConcept C2524010 @default.
• W2989402453 hasConcept C28826006 @default.
• W2989402453 hasConcept C33923547 @default.
• W2989402453 hasConcept C48921125 @default.
• W2989402453 hasConcept C520416788 @default.
• W2989402453 hasConcept C57691317 @default.
• W2989402453 hasConcept C62520636 @default.
• W2989402453 hasConceptScore W2989402453C105795698 @default.
• W2989402453 hasConceptScore W2989402453C114614502 @default.
• W2989402453 hasConceptScore W2989402453C121332964 @default.
• W2989402453 hasConceptScore W2989402453C134306372 @default.
• W2989402453 hasConceptScore W2989402453C155281189 @default.
• W2989402453 hasConceptScore W2989402453C163716315 @default.
• W2989402453 hasConceptScore W2989402453C164226766 @default.
• W2989402453 hasConceptScore W2989402453C20178491 @default.
• W2989402453 hasConceptScore W2989402453C202444582 @default.
• W2989402453 hasConceptScore W2989402453C2524010 @default.
• W2989402453 hasConceptScore W2989402453C28826006 @default.
• W2989402453 hasConceptScore W2989402453C33923547 @default.
• W2989402453 hasConceptScore W2989402453C48921125 @default.
• W2989402453 hasConceptScore W2989402453C520416788 @default.
• W2989402453 hasConceptScore W2989402453C57691317 @default.
• W2989402453 hasConceptScore W2989402453C62520636 @default.
• W2989402453 hasFunder F4320306076 @default.
• W2989402453 hasFunder F4320338281 @default.
• W2989402453 hasIssue "4" @default.
• W2989402453 hasLocation W29894024531 @default.
• W2989402453 hasLocation W29894024532 @default.
• W2989402453 hasLocation W29894024533 @default.
• W2989402453 hasOpenAccess W2989402453 @default.
• W2989402453 hasPrimaryLocation W29894024531 @default.
• W2989402453 hasRelatedWork W1986399599 @default.
• W2989402453 hasRelatedWork W2009425602 @default.
• W2989402453 hasRelatedWork W2039748980 @default.
• W2989402453 hasRelatedWork W2045481834 @default.
• W2989402453 hasRelatedWork W2781510240 @default.
• W2989402453 hasRelatedWork W2949530858 @default.
• W2989402453 hasRelatedWork W2950186459 @default.
• W2989402453 hasRelatedWork W2951776006 @default.

• next