Concept

Down-Weighting Auxiliary Data from a Different Distribution

When an additional training source has a very different distribution from the dev/test set, or when it is much larger than the target-distribution data, the auxiliary examples can be given lower weight. This can reduce the computational burden of making the model do well on both auxiliary and target-distribution examples.

0

1

Updated 2026-05-26

Contributors are:

Who are from:

Tags

Machine Learning

Deep Learning

Supervised Learning

Dive into Deep Learning @ D2L

Data Science

Machine Learning Strategy