Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952327574> ?p ?o ?g. }
- W2952327574 abstract "Real-world machine learning applications often have complex test metrics, and may have training and test data that are not identically distributed. Motivated by known connections between complex test metrics and cost-weighted learning, we propose addressing these issues by using a weighted loss function with a standard loss, where the weights on the training examples are learned to optimize the test metric on a validation set. These metric-optimized example weights can be learned for any test metric, including black box and customized ones for specific applications. We illustrate the performance of the proposed method on diverse public benchmark datasets and real-world applications. We also provide a generalization bound for the method." @default.
- W2952327574 created "2019-06-27" @default.
- W2952327574 creator A5006404251 @default.
- W2952327574 creator A5017397456 @default.
- W2952327574 creator A5064111411 @default.
- W2952327574 creator A5077482746 @default.
- W2952327574 date "2018-05-27" @default.
- W2952327574 modified "2023-09-27" @default.
- W2952327574 title "Metric-Optimized Example Weights" @default.
- W2952327574 cites W1499467920 @default.
- W2952327574 cites W1595159159 @default.
- W2952327574 cites W181733065 @default.
- W2952327574 cites W1850680945 @default.
- W2952327574 cites W1876088969 @default.
- W2952327574 cites W189742998 @default.
- W2952327574 cites W1976526581 @default.
- W2952327574 cites W2018187659 @default.
- W2952327574 cites W2034368206 @default.
- W2952327574 cites W2042587503 @default.
- W2952327574 cites W2070771761 @default.
- W2952327574 cites W2083905053 @default.
- W2952327574 cites W2100495367 @default.
- W2952327574 cites W2102689555 @default.
- W2952327574 cites W2103851188 @default.
- W2952327574 cites W2104144433 @default.
- W2952327574 cites W2107890099 @default.
- W2952327574 cites W2109689843 @default.
- W2952327574 cites W2120100126 @default.
- W2952327574 cites W2121038136 @default.
- W2952327574 cites W2122770142 @default.
- W2952327574 cites W2127176025 @default.
- W2952327574 cites W2129957127 @default.
- W2952327574 cites W2141833813 @default.
- W2952327574 cites W2152195021 @default.
- W2952327574 cites W2167505604 @default.
- W2952327574 cites W2168405694 @default.
- W2952327574 cites W2168639902 @default.
- W2952327574 cites W2170612786 @default.
- W2952327574 cites W2171776966 @default.
- W2952327574 cites W2530395818 @default.
- W2952327574 cites W2616619952 @default.
- W2952327574 cites W2798635843 @default.
- W2952327574 cites W2951054453 @default.
- W2952327574 cites W2952433032 @default.
- W2952327574 cites W2962751370 @default.
- W2952327574 cites W2963327716 @default.
- W2952327574 cites W2963779314 @default.
- W2952327574 cites W2964027161 @default.
- W2952327574 cites W2964121744 @default.
- W2952327574 cites W3125903163 @default.
- W2952327574 cites W340244495 @default.
- W2952327574 hasPublicationYear "2018" @default.
- W2952327574 type Work @default.
- W2952327574 sameAs 2952327574 @default.
- W2952327574 citedByCount "3" @default.
- W2952327574 countsByYear W29523275742019 @default.
- W2952327574 countsByYear W29523275742020 @default.
- W2952327574 crossrefType "posted-content" @default.
- W2952327574 hasAuthorship W2952327574A5006404251 @default.
- W2952327574 hasAuthorship W2952327574A5017397456 @default.
- W2952327574 hasAuthorship W2952327574A5064111411 @default.
- W2952327574 hasAuthorship W2952327574A5077482746 @default.
- W2952327574 hasConcept C105795698 @default.
- W2952327574 hasConcept C11413529 @default.
- W2952327574 hasConcept C119857082 @default.
- W2952327574 hasConcept C122123141 @default.
- W2952327574 hasConcept C124101348 @default.
- W2952327574 hasConcept C127413603 @default.
- W2952327574 hasConcept C13280743 @default.
- W2952327574 hasConcept C134306372 @default.
- W2952327574 hasConcept C14036430 @default.
- W2952327574 hasConcept C141513077 @default.
- W2952327574 hasConcept C151730666 @default.
- W2952327574 hasConcept C154945302 @default.
- W2952327574 hasConcept C169903167 @default.
- W2952327574 hasConcept C176217482 @default.
- W2952327574 hasConcept C177148314 @default.
- W2952327574 hasConcept C177264268 @default.
- W2952327574 hasConcept C185798385 @default.
- W2952327574 hasConcept C199360897 @default.
- W2952327574 hasConcept C205649164 @default.
- W2952327574 hasConcept C21547014 @default.
- W2952327574 hasConcept C2777267654 @default.
- W2952327574 hasConcept C33923547 @default.
- W2952327574 hasConcept C41008148 @default.
- W2952327574 hasConcept C78458016 @default.
- W2952327574 hasConcept C86803240 @default.
- W2952327574 hasConceptScore W2952327574C105795698 @default.
- W2952327574 hasConceptScore W2952327574C11413529 @default.
- W2952327574 hasConceptScore W2952327574C119857082 @default.
- W2952327574 hasConceptScore W2952327574C122123141 @default.
- W2952327574 hasConceptScore W2952327574C124101348 @default.
- W2952327574 hasConceptScore W2952327574C127413603 @default.
- W2952327574 hasConceptScore W2952327574C13280743 @default.
- W2952327574 hasConceptScore W2952327574C134306372 @default.
- W2952327574 hasConceptScore W2952327574C14036430 @default.
- W2952327574 hasConceptScore W2952327574C141513077 @default.
- W2952327574 hasConceptScore W2952327574C151730666 @default.
- W2952327574 hasConceptScore W2952327574C154945302 @default.
- W2952327574 hasConceptScore W2952327574C169903167 @default.