Matches in SemOpenAlex for { <https://semopenalex.org/work/W1553461710> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W1553461710 abstract "In our previous work we have presented an approach to learn interpretable classification rules using a Boolean compressed sensing formulation. Our approach uses a linear programming (LP) relaxation and allows us to find interpretable (sparse) classification rules that achieve good generalization accuracy. However, the resulting LP representation for problems with either a large number of samples or large number of continuous features tends to become challenging for off-the-shelf LP solvers. We have explored a screening approach which allows us to dramatically reduce the number of active features without sacrificing optimality. In this work we explore reducing the number of samples in a sequential setting where we can certify reaching a near-optimal solution while only solving the LP on a small fraction of the available data points. In a batch setting this approach can dramatically reduce the computational complexity of the rule-learning LP formulation. In an online setting we derive stochastic upper and lower bounds on the the LP objective for unseen samples. This allows early stopping when we detect that the classifier will not change significantly with additional samples. The upper bounds are related to the learning curve literature in machine learning, and our lower bounds appear not to have been explored. Finally, we discuss a quick approach to compute the complete regularization path balancing rule interpretability versus accuracy." @default.
- W1553461710 created "2016-06-24" @default.
- W1553461710 creator A5015286159 @default.
- W1553461710 creator A5026795227 @default.
- W1553461710 creator A5048845565 @default.
- W1553461710 date "2015-04-01" @default.
- W1553461710 modified "2023-09-25" @default.
- W1553461710 title "Learning interpretable classification rules using sequential rowsampling" @default.
- W1553461710 cites W134253518 @default.
- W1553461710 cites W135566594 @default.
- W1553461710 cites W1994326354 @default.
- W1553461710 cites W2009772318 @default.
- W1553461710 cites W2069514355 @default.
- W1553461710 cites W2095445014 @default.
- W1553461710 cites W2098902711 @default.
- W1553461710 cites W2103012681 @default.
- W1553461710 cites W2106675197 @default.
- W1553461710 cites W2112118326 @default.
- W1553461710 cites W2118022153 @default.
- W1553461710 cites W2119667497 @default.
- W1553461710 cites W2125412267 @default.
- W1553461710 cites W2151131483 @default.
- W1553461710 cites W2165962877 @default.
- W1553461710 cites W3120740533 @default.
- W1553461710 cites W3148106702 @default.
- W1553461710 doi "https://doi.org/10.1109/icassp.2015.7178589" @default.
- W1553461710 hasPublicationYear "2015" @default.
- W1553461710 type Work @default.
- W1553461710 sameAs 1553461710 @default.
- W1553461710 citedByCount "5" @default.
- W1553461710 countsByYear W15534617102016 @default.
- W1553461710 countsByYear W15534617102017 @default.
- W1553461710 countsByYear W15534617102018 @default.
- W1553461710 countsByYear W15534617102021 @default.
- W1553461710 crossrefType "proceedings-article" @default.
- W1553461710 hasAuthorship W1553461710A5015286159 @default.
- W1553461710 hasAuthorship W1553461710A5026795227 @default.
- W1553461710 hasAuthorship W1553461710A5048845565 @default.
- W1553461710 hasConcept C11413529 @default.
- W1553461710 hasConcept C119857082 @default.
- W1553461710 hasConcept C126255220 @default.
- W1553461710 hasConcept C154945302 @default.
- W1553461710 hasConcept C2776135515 @default.
- W1553461710 hasConcept C2781067378 @default.
- W1553461710 hasConcept C33923547 @default.
- W1553461710 hasConcept C41008148 @default.
- W1553461710 hasConcept C41045048 @default.
- W1553461710 hasConcept C95623464 @default.
- W1553461710 hasConceptScore W1553461710C11413529 @default.
- W1553461710 hasConceptScore W1553461710C119857082 @default.
- W1553461710 hasConceptScore W1553461710C126255220 @default.
- W1553461710 hasConceptScore W1553461710C154945302 @default.
- W1553461710 hasConceptScore W1553461710C2776135515 @default.
- W1553461710 hasConceptScore W1553461710C2781067378 @default.
- W1553461710 hasConceptScore W1553461710C33923547 @default.
- W1553461710 hasConceptScore W1553461710C41008148 @default.
- W1553461710 hasConceptScore W1553461710C41045048 @default.
- W1553461710 hasConceptScore W1553461710C95623464 @default.
- W1553461710 hasLocation W15534617101 @default.
- W1553461710 hasOpenAccess W1553461710 @default.
- W1553461710 hasPrimaryLocation W15534617101 @default.
- W1553461710 hasRelatedWork W2006256533 @default.
- W1553461710 hasRelatedWork W2097575529 @default.
- W1553461710 hasRelatedWork W2540616960 @default.
- W1553461710 hasRelatedWork W2890957505 @default.
- W1553461710 hasRelatedWork W2891606679 @default.
- W1553461710 hasRelatedWork W2951781407 @default.
- W1553461710 hasRelatedWork W2953055478 @default.
- W1553461710 hasRelatedWork W2962891378 @default.
- W1553461710 hasRelatedWork W2963109178 @default.
- W1553461710 hasRelatedWork W2963201025 @default.
- W1553461710 hasRelatedWork W2963763058 @default.
- W1553461710 hasRelatedWork W2966305713 @default.
- W1553461710 hasRelatedWork W2972293876 @default.
- W1553461710 hasRelatedWork W2999688250 @default.
- W1553461710 hasRelatedWork W3049377585 @default.
- W1553461710 hasRelatedWork W3102796955 @default.
- W1553461710 hasRelatedWork W3155603885 @default.
- W1553461710 hasRelatedWork W3163984283 @default.
- W1553461710 hasRelatedWork W3181776142 @default.
- W1553461710 hasRelatedWork W3202132362 @default.
- W1553461710 isParatext "false" @default.
- W1553461710 isRetracted "false" @default.
- W1553461710 magId "1553461710" @default.
- W1553461710 workType "article" @default.