发帖
雷达卡
M ANDOLINE: Model Evaluation under Distribution Shift
Mayee Chen * 1 Karan Goel * 1 Nimit Sohoni * 2 Fait Poms 1 Kayvon Fatahalian 1 Christopher Re 1
Abstract tioners to determine if their models will perform well when
deployed. Unfortunately, standard evaluation falls short
Machine learning models are often deployed in
of this goal on two counts. First, evaluation data is fre-
differ ...
京公网安备 11010802022788号
