Short Answer

Upper bound on error reduction from one source

Question: A document classifier makes 15% of its current mistakes on pages with faint print. Why does that 15% act as a ceiling on the improvement you can get by fully fixing faint-print handling?

Sample answer: It is a ceiling because fixing faint print can remove only the mistakes caused by that issue. If faint print accounts for 15% of the current errors, then even perfect performance on that case can reduce the total error by at most 15% of the current error count. Errors caused by other issues would still remain.

Key points:

  • The fraction for that category is the largest possible reduction from fixing it.
  • Improving one category cannot eliminate errors that come from unrelated causes.

Rubric: The answer should clearly state that the category's error fraction is the maximum possible reduction in overall errors achievable by fixing that category.

0

1

Updated 2026-08-12

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy

Machine Learning Yearning @ DeepLearning.AI