Matthias Feurer, Katharina Eggensperger, Eddie Bergman, Florian Pfisterer, B. Bischl, F. Hutter
{"title":"注意差距:跨多个目标测量泛化性能","authors":"Matthias Feurer, Katharina Eggensperger, Eddie Bergman, Florian Pfisterer, B. Bischl, F. Hutter","doi":"10.48550/arXiv.2212.04183","DOIUrl":null,"url":null,"abstract":"Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such candidate models, and the approximation of the Pareto front is used to assess their performance. In practice, we also want to measure generalization when moving from the validation to the test set. However, some of the models might no longer be Pareto-optimal which makes it unclear how to quantify the performance of the MHPO method when evaluated on the test set. To resolve this, we provide a novel evaluation protocol that allows measuring the generalization performance of MHPO methods and studying its capabilities for comparing two optimization experiments.","PeriodicalId":91439,"journal":{"name":"Advances in intelligent data analysis. International Symposium on Intelligent Data Analysis","volume":"412 1","pages":"130-142"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Mind the Gap: Measuring Generalization Performance Across Multiple Objectives\",\"authors\":\"Matthias Feurer, Katharina Eggensperger, Eddie Bergman, Florian Pfisterer, B. Bischl, F. Hutter\",\"doi\":\"10.48550/arXiv.2212.04183\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such candidate models, and the approximation of the Pareto front is used to assess their performance. In practice, we also want to measure generalization when moving from the validation to the test set. However, some of the models might no longer be Pareto-optimal which makes it unclear how to quantify the performance of the MHPO method when evaluated on the test set. To resolve this, we provide a novel evaluation protocol that allows measuring the generalization performance of MHPO methods and studying its capabilities for comparing two optimization experiments.\",\"PeriodicalId\":91439,\"journal\":{\"name\":\"Advances in intelligent data analysis. International Symposium on Intelligent Data Analysis\",\"volume\":\"412 1\",\"pages\":\"130-142\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-12-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advances in intelligent data analysis. International Symposium on Intelligent Data Analysis\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2212.04183\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in intelligent data analysis. International Symposium on Intelligent Data Analysis","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2212.04183","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Mind the Gap: Measuring Generalization Performance Across Multiple Objectives
Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such candidate models, and the approximation of the Pareto front is used to assess their performance. In practice, we also want to measure generalization when moving from the validation to the test set. However, some of the models might no longer be Pareto-optimal which makes it unclear how to quantify the performance of the MHPO method when evaluated on the test set. To resolve this, we provide a novel evaluation protocol that allows measuring the generalization performance of MHPO methods and studying its capabilities for comparing two optimization experiments.