Matches in SemOpenAlex for { <https://semopenalex.org/work/W2403271036> ?p ?o ?g. }
- W2403271036 endingPage "31" @default.
- W2403271036 startingPage "24" @default.
- W2403271036 abstract "Since hyperparameter optimization is crucial for achieving peak performance with many machine learning algorithms, an active research community has formed around this problem in the last few years. The evaluation of new hyperparameter optimization techniques against the state of the art requires a set of benchmarks. Because such evaluations can be very expensive, early experiments are often performed using synthetic test functions rather than using real-world hyperparameter optimization problems. However, there can be a wide gap between the two kinds of problems. In this work, we introduce another option: cheap-to-evaluate surrogates of real hyperparameter optimization benchmarks that share the same hyperparameter spaces and feature similar response surfaces. Specifically, we train regression models on data describing a machine learning algorithm's performance under a wide range of hyperparameter configurations, and then cheaply evaluate hyperparameter optimization methods using the model's performance predictions in lieu of the real algorithm. We evaluate the effectiveness for using a wide range of regression techniques to build these surrogate benchmarks, both in terms of how well they predict the performance of new configurations and of how much they affect the overall performance of hyperparameter optimizers. Overall, we found that surrogate benchmarks based on random forests performed best: for benchmarks with few hyperparameters they yielded almost perfect surrogates, and for benchmarks with more complex hyperparameter spaces they still yielded surrogates that were qualitatively similar to the real benchmarks they model." @default.
- W2403271036 created "2016-06-24" @default.
- W2403271036 creator A5025342513 @default.
- W2403271036 creator A5031002895 @default.
- W2403271036 creator A5081813991 @default.
- W2403271036 creator A5089807699 @default.
- W2403271036 date "2014-09-19" @default.
- W2403271036 modified "2023-09-26" @default.
- W2403271036 title "Surrogate benchmarks for hyperparameter optimization" @default.
- W2403271036 cites W116375701 @default.
- W2403271036 cites W1567512734 @default.
- W2403271036 cites W1571472016 @default.
- W2403271036 cites W1593343777 @default.
- W2403271036 cites W1994197834 @default.
- W2403271036 cites W2018044188 @default.
- W2403271036 cites W2045463058 @default.
- W2403271036 cites W2086056248 @default.
- W2403271036 cites W2090136295 @default.
- W2403271036 cites W2097998348 @default.
- W2403271036 cites W2099201756 @default.
- W2403271036 cites W2101234009 @default.
- W2403271036 cites W2102539288 @default.
- W2403271036 cites W2106411961 @default.
- W2403271036 cites W2106944478 @default.
- W2403271036 cites W2112364454 @default.
- W2403271036 cites W2112796928 @default.
- W2403271036 cites W2113207845 @default.
- W2403271036 cites W2131241448 @default.
- W2403271036 cites W2147196093 @default.
- W2403271036 cites W2165599843 @default.
- W2403271036 cites W2171263583 @default.
- W2403271036 cites W2618530766 @default.
- W2403271036 cites W2950680102 @default.
- W2403271036 cites W3118608800 @default.
- W2403271036 cites W60686164 @default.
- W2403271036 cites W76331760 @default.
- W2403271036 hasPublicationYear "2014" @default.
- W2403271036 type Work @default.
- W2403271036 sameAs 2403271036 @default.
- W2403271036 citedByCount "5" @default.
- W2403271036 countsByYear W24032710362015 @default.
- W2403271036 countsByYear W24032710362018 @default.
- W2403271036 countsByYear W24032710362020 @default.
- W2403271036 countsByYear W24032710362021 @default.
- W2403271036 crossrefType "journal-article" @default.
- W2403271036 hasAuthorship W2403271036A5025342513 @default.
- W2403271036 hasAuthorship W2403271036A5031002895 @default.
- W2403271036 hasAuthorship W2403271036A5081813991 @default.
- W2403271036 hasAuthorship W2403271036A5089807699 @default.
- W2403271036 hasConcept C10485038 @default.
- W2403271036 hasConcept C105795698 @default.
- W2403271036 hasConcept C119857082 @default.
- W2403271036 hasConcept C12267149 @default.
- W2403271036 hasConcept C127413603 @default.
- W2403271036 hasConcept C146978453 @default.
- W2403271036 hasConcept C154945302 @default.
- W2403271036 hasConcept C177264268 @default.
- W2403271036 hasConcept C199360897 @default.
- W2403271036 hasConcept C204323151 @default.
- W2403271036 hasConcept C33923547 @default.
- W2403271036 hasConcept C41008148 @default.
- W2403271036 hasConcept C83546350 @default.
- W2403271036 hasConcept C8642999 @default.
- W2403271036 hasConceptScore W2403271036C10485038 @default.
- W2403271036 hasConceptScore W2403271036C105795698 @default.
- W2403271036 hasConceptScore W2403271036C119857082 @default.
- W2403271036 hasConceptScore W2403271036C12267149 @default.
- W2403271036 hasConceptScore W2403271036C127413603 @default.
- W2403271036 hasConceptScore W2403271036C146978453 @default.
- W2403271036 hasConceptScore W2403271036C154945302 @default.
- W2403271036 hasConceptScore W2403271036C177264268 @default.
- W2403271036 hasConceptScore W2403271036C199360897 @default.
- W2403271036 hasConceptScore W2403271036C204323151 @default.
- W2403271036 hasConceptScore W2403271036C33923547 @default.
- W2403271036 hasConceptScore W2403271036C41008148 @default.
- W2403271036 hasConceptScore W2403271036C83546350 @default.
- W2403271036 hasConceptScore W2403271036C8642999 @default.
- W2403271036 hasLocation W24032710361 @default.
- W2403271036 hasOpenAccess W2403271036 @default.
- W2403271036 hasPrimaryLocation W24032710361 @default.
- W2403271036 hasRelatedWork W2097998348 @default.
- W2403271036 hasRelatedWork W2106411961 @default.
- W2403271036 hasRelatedWork W2296059279 @default.
- W2403271036 hasRelatedWork W2405658191 @default.
- W2403271036 hasRelatedWork W2775233965 @default.
- W2403271036 hasRelatedWork W2782093256 @default.
- W2403271036 hasRelatedWork W2888999015 @default.
- W2403271036 hasRelatedWork W2912851808 @default.
- W2403271036 hasRelatedWork W2919302225 @default.
- W2403271036 hasRelatedWork W2944786596 @default.
- W2403271036 hasRelatedWork W2954882791 @default.
- W2403271036 hasRelatedWork W2973091465 @default.
- W2403271036 hasRelatedWork W3011618419 @default.
- W2403271036 hasRelatedWork W3029879778 @default.
- W2403271036 hasRelatedWork W3092207651 @default.
- W2403271036 hasRelatedWork W3093798922 @default.
- W2403271036 hasRelatedWork W3099018856 @default.
- W2403271036 hasRelatedWork W3129764450 @default.