{"type":"ScholarlyArticle","title":"Adaptive Dropout Rates for Learning with Corrupted Features","authors":[{"name":"Jingwei Zhuo","slug":"jingwei-zhuo","given":"Jingwei","family":"Zhuo","affiliation":""},{"name":"Jun Zhu","slug":"jun-zhu-2","given":"Jun","family":"Zhu","affiliation":""},{"name":"Bo Zhang","slug":"bo-zhang","given":"Bo","family":"Zhang","affiliation":""}],"abstract":"Feature noising is an effective mechanism on reducing the risk of overfitting. To avoid an explosive searching space, existing work typically assumes that all features share a single noise level, which is often cross-validated. In this paper, we present a Bayesian feature noising model that flexibly allows for dimension-specific or group-specific noise levels, and we derive a learning algorithm that adaptively updates these noise levels. Our adaptive rule is simple and interpretable, by drawing a direct connection to the fitness of each individual feature or feature group. Empirical results on various datasets demonstrate the effectiveness on avoiding extensive tuning and sometimes improving the performance due to its flexibility.","doi":null,"url":"https://ijcai.org/proceedings/2015/579","pdf":"https://ijcai.org/proceedings/2015/0579.pdf","markdown":"https://ijcai.org/proceedings/2015/579.md","bibtex":"https://ijcai.org/proceedings/2015/bibtex/579","volume":{"slug":"2015","title":"Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2015","url":"https://ijcai.org/proceedings/2015/","year":2015,"location":"Buenos Aires, Argentina","dates":"25–31 July 2015","editors":"Qiang Yang and Michael Wooldridge","isbn":"978-1-57735-738-4","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Special Track on Machine Learning","track":"Special Track on Machine Learning","number":579,"pages":{"first":4126,"last":4132},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}