Matches in SemOpenAlex for { <https://semopenalex.org/work/W2276735006> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2276735006 abstract "Modern data science relies on data analytic pipelines to organize interdependent computational steps. Such analytic pipelines often involve different algorithms across multiple steps, each with its own hyperparameters. To achieve the best performance, it is often critical to select optimal algorithms and to set appropriate hyperparameters, which requires large computational efforts. Bayesian optimization provides a principled way for searching optimal hyperparameters for a single algorithm. However, many challenges remain in solving pipeline optimization problems with high-dimensional and highly conditional search space. In this work, we propose Fast LineAr SearcH (FLASH), an efficient method for tuning analytic pipelines. FLASH is a two-layer Bayesian optimization framework, which firstly uses a parametric model to select promising algorithms, then computes a nonparametric model to fine-tune hyperparameters of the promising algorithms. FLASH also includes an effective caching algorithm which can further accelerate the search process. Extensive experiments on a number of benchmark datasets have demonstrated that FLASH significantly outperforms previous state-of-the-art methods in both search speed and accuracy. Using 50% of the time budget, FLASH achieves up to 20% improvement on test error rate compared to the baselines. FLASH also yields state-of-the-art performance on a real-world application for healthcare predictive modeling." @default.
- W2276735006 created "2016-06-24" @default.
- W2276735006 creator A5015663174 @default.
- W2276735006 creator A5043340297 @default.
- W2276735006 creator A5076420985 @default.
- W2276735006 creator A5084279065 @default.
- W2276735006 date "2016-08-13" @default.
- W2276735006 modified "2023-10-16" @default.
- W2276735006 title "FLASH" @default.
- W2276735006 cites W1969116741 @default.
- W2276735006 cites W1981265575 @default.
- W2276735006 cites W2020732830 @default.
- W2276735006 cites W2073110021 @default.
- W2276735006 cites W2100729440 @default.
- W2276735006 cites W2102539288 @default.
- W2276735006 cites W2120448874 @default.
- W2276735006 cites W2130941826 @default.
- W2276735006 cites W2132651631 @default.
- W2276735006 cites W2133990480 @default.
- W2276735006 cites W2135514714 @default.
- W2276735006 cites W2192203593 @default.
- W2276735006 cites W2214709429 @default.
- W2276735006 cites W2357449897 @default.
- W2276735006 cites W4246784033 @default.
- W2276735006 cites W60686164 @default.
- W2276735006 doi "https://doi.org/10.1145/2939672.2939829" @default.
- W2276735006 hasPublicationYear "2016" @default.
- W2276735006 type Work @default.
- W2276735006 sameAs 2276735006 @default.
- W2276735006 citedByCount "22" @default.
- W2276735006 countsByYear W22767350062016 @default.
- W2276735006 countsByYear W22767350062017 @default.
- W2276735006 countsByYear W22767350062018 @default.
- W2276735006 countsByYear W22767350062019 @default.
- W2276735006 countsByYear W22767350062020 @default.
- W2276735006 countsByYear W22767350062021 @default.
- W2276735006 countsByYear W22767350062022 @default.
- W2276735006 countsByYear W22767350062023 @default.
- W2276735006 crossrefType "proceedings-article" @default.
- W2276735006 hasAuthorship W2276735006A5015663174 @default.
- W2276735006 hasAuthorship W2276735006A5043340297 @default.
- W2276735006 hasAuthorship W2276735006A5076420985 @default.
- W2276735006 hasAuthorship W2276735006A5084279065 @default.
- W2276735006 hasConcept C11413529 @default.
- W2276735006 hasConcept C119857082 @default.
- W2276735006 hasConcept C124101348 @default.
- W2276735006 hasConcept C127413603 @default.
- W2276735006 hasConcept C13280743 @default.
- W2276735006 hasConcept C154945302 @default.
- W2276735006 hasConcept C175309249 @default.
- W2276735006 hasConcept C185798385 @default.
- W2276735006 hasConcept C199360897 @default.
- W2276735006 hasConcept C205649164 @default.
- W2276735006 hasConcept C2778049539 @default.
- W2276735006 hasConcept C41008148 @default.
- W2276735006 hasConcept C43521106 @default.
- W2276735006 hasConcept C8642999 @default.
- W2276735006 hasConcept C87717796 @default.
- W2276735006 hasConceptScore W2276735006C11413529 @default.
- W2276735006 hasConceptScore W2276735006C119857082 @default.
- W2276735006 hasConceptScore W2276735006C124101348 @default.
- W2276735006 hasConceptScore W2276735006C127413603 @default.
- W2276735006 hasConceptScore W2276735006C13280743 @default.
- W2276735006 hasConceptScore W2276735006C154945302 @default.
- W2276735006 hasConceptScore W2276735006C175309249 @default.
- W2276735006 hasConceptScore W2276735006C185798385 @default.
- W2276735006 hasConceptScore W2276735006C199360897 @default.
- W2276735006 hasConceptScore W2276735006C205649164 @default.
- W2276735006 hasConceptScore W2276735006C2778049539 @default.
- W2276735006 hasConceptScore W2276735006C41008148 @default.
- W2276735006 hasConceptScore W2276735006C43521106 @default.
- W2276735006 hasConceptScore W2276735006C8642999 @default.
- W2276735006 hasConceptScore W2276735006C87717796 @default.
- W2276735006 hasLocation W22767350061 @default.
- W2276735006 hasOpenAccess W2276735006 @default.
- W2276735006 hasPrimaryLocation W22767350061 @default.
- W2276735006 hasRelatedWork W2200000192 @default.
- W2276735006 hasRelatedWork W2405673391 @default.
- W2276735006 hasRelatedWork W2782093256 @default.
- W2276735006 hasRelatedWork W2783569492 @default.
- W2276735006 hasRelatedWork W2963474950 @default.
- W2276735006 hasRelatedWork W3155731460 @default.
- W2276735006 hasRelatedWork W3198858656 @default.
- W2276735006 hasRelatedWork W3199608561 @default.
- W2276735006 hasRelatedWork W3214139057 @default.
- W2276735006 hasRelatedWork W4313434626 @default.
- W2276735006 isParatext "false" @default.
- W2276735006 isRetracted "false" @default.
- W2276735006 magId "2276735006" @default.
- W2276735006 workType "article" @default.