FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2597892042> ?p ?o ?g. }

• W2597892042 abstract "The cyclic block coordinate descent-type (CBCD-type) methods, which performs iterative updates for a few coordinates (a block) simultaneously throughout the procedure, have shown remarkable computational performance for solving strongly convex minimization problems. Typical applications include many popular statistical machine learning methods such as elastic-net regression, ridge penalized logistic regression, and sparse additive regression. Existing optimization literature has shown that for strongly convex minimization, the CBCD-type methods attain iteration complexity of $mathcal{O}(plog(1/epsilon))$, where $epsilon$ is a pre-specified accuracy of the objective value, and $p$ is the number of blocks. However, such iteration complexity explicitly depends on $p$, and therefore is at least $p$ times worse than the complexity $mathcal{O}(log(1/epsilon))$ of gradient descent (GD) methods. To bridge this theoretical gap, we propose an improved convergence analysis for the CBCD-type methods. In particular, we first show that for a family of quadratic minimization problems, the iteration complexity $mathcal{O}(log^2(p)cdotlog(1/epsilon))$ of the CBCD-type methods matches that of the GD methods in term of dependency on $p$, up to a $log^2 p$ factor. Thus our complexity bounds are sharper than the existing bounds by at least a factor of $p/log^2(p)$. We also provide a lower bound to confirm that our improved complexity bounds are tight (up to a $log^2 (p)$ factor), under the assumption that the largest and smallest eigenvalues of the Hessian matrix do not scale with $p$. Finally, we generalize our analysis to other strongly convex minimization problems beyond quadratic ones." @default.
• W2597892042 created "2017-04-07" @default.
• W2597892042 creator A5016900183 @default.
• W2597892042 creator A5019708503 @default.
• W2597892042 creator A5022338996 @default.
• W2597892042 creator A5028930379 @default.
• W2597892042 creator A5063457506 @default.
• W2597892042 date "2016-07-10" @default.
• W2597892042 modified "2023-09-28" @default.
• W2597892042 title "On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization" @default.
• W2597892042 cites W1480376833 @default.
• W2597892042 cites W1871644925 @default.
• W2597892042 cites W1921133930 @default.
• W2597892042 cites W1965169081 @default.
• W2597892042 cites W1969048569 @default.
• W2597892042 cites W1974524469 @default.
• W2597892042 cites W2023901033 @default.
• W2597892042 cites W2039050532 @default.
• W2597892042 cites W2041815422 @default.
• W2597892042 cites W2045079045 @default.
• W2597892042 cites W2050968963 @default.
• W2597892042 cites W2064066631 @default.
• W2597892042 cites W2075660001 @default.
• W2597892042 cites W2090084467 @default.
• W2597892042 cites W2097360283 @default.
• W2597892042 cites W2100556411 @default.
• W2597892042 cites W2101631795 @default.
• W2597892042 cites W2118545728 @default.
• W2597892042 cites W2122825543 @default.
• W2597892042 cites W2125156589 @default.
• W2597892042 cites W2125390510 @default.
• W2597892042 cites W2131060185 @default.
• W2597892042 cites W2138228305 @default.
• W2597892042 cites W2142224912 @default.
• W2597892042 cites W2144115358 @default.
• W2597892042 cites W2164278908 @default.
• W2597892042 cites W2331905737 @default.
• W2597892042 cites W2343345052 @default.
• W2597892042 cites W2405330762 @default.
• W2597892042 cites W2504151877 @default.
• W2597892042 cites W2528674465 @default.
• W2597892042 cites W2949437147 @default.
• W2597892042 cites W2950663096 @default.
• W2597892042 cites W2951002577 @default.
• W2597892042 cites W2963108795 @default.
• W2597892042 cites W3141595720 @default.
• W2597892042 cites W267850302 @default.
• W2597892042 hasPublicationYear "2016" @default.
• W2597892042 type Work @default.
• W2597892042 sameAs 2597892042 @default.
• W2597892042 citedByCount "1" @default.
• W2597892042 countsByYear W25978920422016 @default.
• W2597892042 crossrefType "posted-content" @default.
• W2597892042 hasAuthorship W2597892042A5016900183 @default.
• W2597892042 hasAuthorship W2597892042A5019708503 @default.
• W2597892042 hasAuthorship W2597892042A5022338996 @default.
• W2597892042 hasAuthorship W2597892042A5028930379 @default.
• W2597892042 hasAuthorship W2597892042A5063457506 @default.
• W2597892042 hasConcept C106487976 @default.
• W2597892042 hasConcept C112680207 @default.
• W2597892042 hasConcept C11413529 @default.
• W2597892042 hasConcept C114614502 @default.
• W2597892042 hasConcept C118615104 @default.
• W2597892042 hasConcept C126255220 @default.
• W2597892042 hasConcept C129844170 @default.
• W2597892042 hasConcept C134306372 @default.
• W2597892042 hasConcept C145446738 @default.
• W2597892042 hasConcept C147764199 @default.
• W2597892042 hasConcept C157553263 @default.
• W2597892042 hasConcept C157972887 @default.
• W2597892042 hasConcept C159985019 @default.
• W2597892042 hasConcept C162324750 @default.
• W2597892042 hasConcept C179799912 @default.
• W2597892042 hasConcept C18903297 @default.
• W2597892042 hasConcept C192562407 @default.
• W2597892042 hasConcept C203616005 @default.
• W2597892042 hasConcept C2524010 @default.
• W2597892042 hasConcept C2777210771 @default.
• W2597892042 hasConcept C2777299769 @default.
• W2597892042 hasConcept C2777303404 @default.
• W2597892042 hasConcept C28826006 @default.
• W2597892042 hasConcept C33923547 @default.
• W2597892042 hasConcept C50522688 @default.
• W2597892042 hasConcept C63553672 @default.
• W2597892042 hasConcept C77553402 @default.
• W2597892042 hasConcept C86803240 @default.
• W2597892042 hasConceptScore W2597892042C106487976 @default.
• W2597892042 hasConceptScore W2597892042C112680207 @default.
• W2597892042 hasConceptScore W2597892042C11413529 @default.
• W2597892042 hasConceptScore W2597892042C114614502 @default.
• W2597892042 hasConceptScore W2597892042C118615104 @default.
• W2597892042 hasConceptScore W2597892042C126255220 @default.
• W2597892042 hasConceptScore W2597892042C129844170 @default.
• W2597892042 hasConceptScore W2597892042C134306372 @default.
• W2597892042 hasConceptScore W2597892042C145446738 @default.
• W2597892042 hasConceptScore W2597892042C147764199 @default.
• W2597892042 hasConceptScore W2597892042C157553263 @default.
• W2597892042 hasConceptScore W2597892042C157972887 @default.
• W2597892042 hasConceptScore W2597892042C159985019 @default.
• W2597892042 hasConceptScore W2597892042C162324750 @default.

• next