Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288792244> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4288792244 abstract "Unlike its intercept, a linear classifier's weight vector cannot be tuned by a simple grid search. Hence, this paper proposes weight vector tuning of a generic binary linear classifier through the parameterization of a decomposition of the discriminant by a scalar which controls the trade-off between conflicting informative and noisy terms. By varying this parameter, the original weight vector is modified in a meaningful way. Applying this method to a number of linear classifiers under a variety of data dimensionality and sample size settings reveals that the classification performance loss due to non-optimal native hyperparameters can be compensated for by weight vector tuning. This yields computational savings as the proposed tuning method reduces to tuning a scalar compared to tuning the native hyperparameter, which may involve repeated weight vector generation along with its burden of optimization, dimensionality reduction, etc., depending on the classifier. It is also found that weight vector tuning significantly improves the performance of Linear Discriminant Analysis (LDA) under high estimation noise. Proceeding from this second finding, an asymptotic study of the misclassification probability of the parameterized LDA classifier in the growth regime where the data dimensionality and sample size are comparable is conducted. Using random matrix theory, the misclassification probability is shown to converge to a quantity that is a function of the true statistics of the data. Additionally, an estimator of the misclassification probability is derived. Finally, computationally efficient tuning of the parameter using this estimator is demonstrated on real data." @default.
- W4288792244 created "2022-07-30" @default.
- W4288792244 creator A5006716265 @default.
- W4288792244 creator A5046626829 @default.
- W4288792244 creator A5053632308 @default.
- W4288792244 creator A5066119580 @default.
- W4288792244 creator A5083193286 @default.
- W4288792244 date "2021-10-01" @default.
- W4288792244 modified "2023-10-16" @default.
- W4288792244 title "Weight Vector Tuning and Asymptotic Analysis of Binary Linear Classifiers" @default.
- W4288792244 doi "https://doi.org/10.48550/arxiv.2110.00567" @default.
- W4288792244 hasPublicationYear "2021" @default.
- W4288792244 type Work @default.
- W4288792244 citedByCount "0" @default.
- W4288792244 crossrefType "posted-content" @default.
- W4288792244 hasAuthorship W4288792244A5006716265 @default.
- W4288792244 hasAuthorship W4288792244A5046626829 @default.
- W4288792244 hasAuthorship W4288792244A5053632308 @default.
- W4288792244 hasAuthorship W4288792244A5066119580 @default.
- W4288792244 hasAuthorship W4288792244A5083193286 @default.
- W4288792244 hasBestOaLocation W42887922441 @default.
- W4288792244 hasConcept C10485038 @default.
- W4288792244 hasConcept C105795698 @default.
- W4288792244 hasConcept C111030470 @default.
- W4288792244 hasConcept C11413529 @default.
- W4288792244 hasConcept C12267149 @default.
- W4288792244 hasConcept C129848803 @default.
- W4288792244 hasConcept C139532973 @default.
- W4288792244 hasConcept C153180895 @default.
- W4288792244 hasConcept C154945302 @default.
- W4288792244 hasConcept C183877218 @default.
- W4288792244 hasConcept C185429906 @default.
- W4288792244 hasConcept C202444582 @default.
- W4288792244 hasConcept C33923547 @default.
- W4288792244 hasConcept C41008148 @default.
- W4288792244 hasConcept C48372109 @default.
- W4288792244 hasConcept C51568863 @default.
- W4288792244 hasConcept C66905080 @default.
- W4288792244 hasConcept C69738355 @default.
- W4288792244 hasConcept C70518039 @default.
- W4288792244 hasConcept C8642999 @default.
- W4288792244 hasConcept C94375191 @default.
- W4288792244 hasConcept C95623464 @default.
- W4288792244 hasConceptScore W4288792244C10485038 @default.
- W4288792244 hasConceptScore W4288792244C105795698 @default.
- W4288792244 hasConceptScore W4288792244C111030470 @default.
- W4288792244 hasConceptScore W4288792244C11413529 @default.
- W4288792244 hasConceptScore W4288792244C12267149 @default.
- W4288792244 hasConceptScore W4288792244C129848803 @default.
- W4288792244 hasConceptScore W4288792244C139532973 @default.
- W4288792244 hasConceptScore W4288792244C153180895 @default.
- W4288792244 hasConceptScore W4288792244C154945302 @default.
- W4288792244 hasConceptScore W4288792244C183877218 @default.
- W4288792244 hasConceptScore W4288792244C185429906 @default.
- W4288792244 hasConceptScore W4288792244C202444582 @default.
- W4288792244 hasConceptScore W4288792244C33923547 @default.
- W4288792244 hasConceptScore W4288792244C41008148 @default.
- W4288792244 hasConceptScore W4288792244C48372109 @default.
- W4288792244 hasConceptScore W4288792244C51568863 @default.
- W4288792244 hasConceptScore W4288792244C66905080 @default.
- W4288792244 hasConceptScore W4288792244C69738355 @default.
- W4288792244 hasConceptScore W4288792244C70518039 @default.
- W4288792244 hasConceptScore W4288792244C8642999 @default.
- W4288792244 hasConceptScore W4288792244C94375191 @default.
- W4288792244 hasConceptScore W4288792244C95623464 @default.
- W4288792244 hasLocation W42887922441 @default.
- W4288792244 hasOpenAccess W4288792244 @default.
- W4288792244 hasPrimaryLocation W42887922441 @default.
- W4288792244 hasRelatedWork W12370636 @default.
- W4288792244 hasRelatedWork W12648998 @default.
- W4288792244 hasRelatedWork W12728872 @default.
- W4288792244 hasRelatedWork W1781265 @default.
- W4288792244 hasRelatedWork W4533635 @default.
- W4288792244 hasRelatedWork W6057950 @default.
- W4288792244 hasRelatedWork W7299809 @default.
- W4288792244 hasRelatedWork W8718456 @default.
- W4288792244 hasRelatedWork W9557556 @default.
- W4288792244 hasRelatedWork W9686548 @default.
- W4288792244 isParatext "false" @default.
- W4288792244 isRetracted "false" @default.
- W4288792244 workType "article" @default.