4.7. Environment and Distribution Shift — Dive into Deep Learning 1.0.3 documentation thumbnail
4.7. Environment and Distribution Shift — Dive into Deep Learning 1.0.3 documentation
d2l.ai
by introducing our model-based decisions to the environment, we might break the model. distribution of inputs may change over time Statisticians call this covariate shift because the problem arises due to a shift in the distribution of the covariates (features). Label shift describes the converse pr
2 Users
0 Comments
51 Highlights
0 Notes

Top Highlights

  • by introducing our model-based decisions to the environment, we might break the model.
  • distribution of inputs may change over time
  • Statisticians call this covariate shift because the problem arises due to a shift in the distribution of the covariates (features).
  • Label shift describes the converse problem. Here, we assume that the label marginal
  • degenerate cases the label shift and covariate shift assumptions can hold simultaneously.

Domain

Ready to highlight and find good content?

Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.