* Tags:: Book (still not read) * Author:: [[aston-zhang|Aston Zhang]], [[zach-c.-lipton|Zach C]], [[mu-li|Mu Li]], [[alex-j.-smola|Alex J]] (Amazon Data Scientists) * Link:: [Dive into Deep Learning — Dive into Deep Learning 0.17.2 documentation (d2l.ai)](https://d2l.ai/index.html) * Source date:: [[2021-01-01]] * Finished date:: [[2021-01-06]] ## 4.9 Environment and Distribution Drift [[Covariate shift|Covariate shift]]: That p(x|y) remains constant is an assumption we make, and we do so in circumstances where we believe that x causes y. [[Label shift|Label Shift]]: That p(y|x) remains constant is an assumption we make in cases where we believe that y causes x (disease -> symptoms). [[Model drifting|Model Drifting]]: We may also have a third case, [[Concept drift|Concept drift]], where the very definition of "y" may change. The only thing we can do is exploit knowledge of those variations being very gradual in time, space...