Matches in SemOpenAlex for { <https://semopenalex.org/work/W2404639568> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2404639568 abstract "The recent years have witnessed advances in parallel algorithms for large scale optimization problems. Notwithstanding demonstrated success, existing algorithms that parallelize over features are usually limited by divergence issues under high parallelism or require data preprocessing to alleviate these problems. In this work, we propose a Parallel Coordinate Descent Newton algorithm using multidimensional approximate Newton steps (PCDN), where the off-diagonal elements of the Hessian are set to zero to enable parallelization. It randomly partitions the feature set into $b$ bundles/subsets with size of $P$, and sequentially processes each bundle by first computing the descent directions for each feature in parallel and then conducting $P$-dimensional line search to obtain the step size. We show that: (1) PCDN is guaranteed to converge globally despite increasing parallelism; (2) PCDN converges to the specified accuracy $epsilon$ within the limited iteration number of $T_epsilon$, and $T_epsilon$ decreases with increasing parallelism (bundle size $P$). Using the implementation technique of maintaining intermediate quantities, we minimize the data transfer and synchronization cost of the $P$-dimensional line search. For concreteness, the proposed PCDN algorithm is applied to $ell_1$-regularized logistic regression and $ell_2$-loss SVM. Experimental evaluations on six benchmark datasets show that the proposed PCDN algorithm exploits parallelism well and outperforms the state-of-the-art methods in speed without losing accuracy." @default.
- W2404639568 created "2016-06-24" @default.
- W2404639568 creator A5011875487 @default.
- W2404639568 creator A5045777220 @default.
- W2404639568 creator A5061110835 @default.
- W2404639568 date "2013-06-18" @default.
- W2404639568 modified "2023-09-26" @default.
- W2404639568 title "Parallel Coordinate Descent Newton for Large-scale L1-Regularized Minimization." @default.
- W2404639568 hasPublicationYear "2013" @default.
- W2404639568 type Work @default.
- W2404639568 sameAs 2404639568 @default.
- W2404639568 citedByCount "4" @default.
- W2404639568 countsByYear W24046395682013 @default.
- W2404639568 countsByYear W24046395682014 @default.
- W2404639568 countsByYear W24046395682015 @default.
- W2404639568 crossrefType "posted-content" @default.
- W2404639568 hasAuthorship W2404639568A5011875487 @default.
- W2404639568 hasAuthorship W2404639568A5045777220 @default.
- W2404639568 hasAuthorship W2404639568A5061110835 @default.
- W2404639568 hasConcept C11413529 @default.
- W2404639568 hasConcept C13280743 @default.
- W2404639568 hasConcept C157553263 @default.
- W2404639568 hasConcept C173608175 @default.
- W2404639568 hasConcept C178635117 @default.
- W2404639568 hasConcept C185798385 @default.
- W2404639568 hasConcept C203616005 @default.
- W2404639568 hasConcept C205649164 @default.
- W2404639568 hasConcept C28826006 @default.
- W2404639568 hasConcept C33923547 @default.
- W2404639568 hasConcept C38652104 @default.
- W2404639568 hasConcept C41008148 @default.
- W2404639568 hasConcept C85522705 @default.
- W2404639568 hasConceptScore W2404639568C11413529 @default.
- W2404639568 hasConceptScore W2404639568C13280743 @default.
- W2404639568 hasConceptScore W2404639568C157553263 @default.
- W2404639568 hasConceptScore W2404639568C173608175 @default.
- W2404639568 hasConceptScore W2404639568C178635117 @default.
- W2404639568 hasConceptScore W2404639568C185798385 @default.
- W2404639568 hasConceptScore W2404639568C203616005 @default.
- W2404639568 hasConceptScore W2404639568C205649164 @default.
- W2404639568 hasConceptScore W2404639568C28826006 @default.
- W2404639568 hasConceptScore W2404639568C33923547 @default.
- W2404639568 hasConceptScore W2404639568C38652104 @default.
- W2404639568 hasConceptScore W2404639568C41008148 @default.
- W2404639568 hasConceptScore W2404639568C85522705 @default.
- W2404639568 hasLocation W24046395681 @default.
- W2404639568 hasOpenAccess W2404639568 @default.
- W2404639568 hasPrimaryLocation W24046395681 @default.
- W2404639568 hasRelatedWork W1507755051 @default.
- W2404639568 hasRelatedWork W1667264917 @default.
- W2404639568 hasRelatedWork W1839876751 @default.
- W2404639568 hasRelatedWork W1939652453 @default.
- W2404639568 hasRelatedWork W2084453552 @default.
- W2404639568 hasRelatedWork W2095984592 @default.
- W2404639568 hasRelatedWork W2114643899 @default.
- W2404639568 hasRelatedWork W2138995291 @default.
- W2404639568 hasRelatedWork W2142623206 @default.
- W2404639568 hasRelatedWork W2159915812 @default.
- W2404639568 hasRelatedWork W2293249015 @default.
- W2404639568 hasRelatedWork W2770362671 @default.
- W2404639568 hasRelatedWork W2788408502 @default.
- W2404639568 hasRelatedWork W2883309838 @default.
- W2404639568 hasRelatedWork W2888562580 @default.
- W2404639568 hasRelatedWork W2901664571 @default.
- W2404639568 hasRelatedWork W2963911159 @default.
- W2404639568 hasRelatedWork W3030121914 @default.
- W2404639568 hasRelatedWork W3133001235 @default.
- W2404639568 hasRelatedWork W3173530920 @default.
- W2404639568 isParatext "false" @default.
- W2404639568 isRetracted "false" @default.
- W2404639568 magId "2404639568" @default.
- W2404639568 workType "article" @default.