Proceedings of the 2020 ACM-IMS on Foundations of Data Science Conference最新文献_第3页

Statistical Significance in High-dimensional Linear Mixed Models 高维线性混合模型的统计显著性

Proceedings of the 2020 ACM-IMS on Foundations of Data Science Conference Pub Date : 2019-12-16 DOI: 10.1145/3412815.3416883

Lina Lin, M. Drton, A. Shojaie

引用次数: 5

Interpreting Black Box Models via Hypothesis Testing 通过假设检验解释黑盒模型

Proceedings of the 2020 ACM-IMS on Foundations of Data Science Conference Pub Date : 2019-03-29 DOI: 10.1145/3412815.3416889

Collin Burns, Jesse Thomason, Wesley Tansey

{"title":"Interpreting Black Box Models via Hypothesis Testing","authors":"Collin Burns, Jesse Thomason, Wesley Tansey","doi":"10.1145/3412815.3416889","DOIUrl":"https://doi.org/10.1145/3412815.3416889","url":null,"abstract":"In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries may lead investigators astray. These applications would therefore benefit from control over the finite-sample error rate of interpretations. We reframe black box model interpretability as a multiple hypothesis testing problem. The task is to discover \"important\" features by testing whether the model prediction is significantly different from what would be expected if the features were replaced with uninformative counterfactuals. We propose two testing methods: one that provably controls the false discovery rate but which is not yet feasible for large-scale applications, and an approximate testing method which can be applied to real-world data sets. In simulation, both tests have high power relative to existing interpretability methods. When applied to state-of-the-art vision and language models, the framework selects features that intuitively explain model predictions. The resulting explanations have the additional advantage that they are themselves easy to interpret.","PeriodicalId":176130,"journal":{"name":"Proceedings of the 2020 ACM-IMS on Foundations of Data Science Conference","volume":"48 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132690687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 39

Towards Practical Lipschitz Bandits 实用Lipschitz土匪

Proceedings of the 2020 ACM-IMS on Foundations of Data Science Conference Pub Date : 2019-01-26 DOI: 10.1145/3412815.3416885

Tianyu Wang, Weicheng Ye, Dawei Geng, C. Rudin

引用次数: 14

Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable 树空间原型:另一个看使树集成可解释

Proceedings of the 2020 ACM-IMS on Foundations of Data Science Conference Pub Date : 2016-11-22 DOI: 10.1145/3412815.3416893

S. Tan, Matvey Soloviev, G. Hooker, M. Wells

引用次数: 50